Triple
T14090953
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Tsing Hua University |
E339127
|
entity |
| Predicate | memberOf |
P10
|
FINISHED |
| Object |
Global Learning and Observations to Benefit the Environment (GLOBE) program (via Taiwan)
The Global Learning and Observations to Benefit the Environment (GLOBE) program is an international, school-based science and education initiative that engages students, teachers, and scientists in collaborative environmental data collection and research.
|
E1080270
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Global Learning and Observations to Benefit the Environment (GLOBE) program (via Taiwan) | Statement: [National Tsing Hua University, memberOf, Global Learning and Observations to Benefit the Environment (GLOBE) program (via Taiwan)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Global Learning and Observations to Benefit the Environment (GLOBE) program (via Taiwan) Context triple: [National Tsing Hua University, memberOf, Global Learning and Observations to Benefit the Environment (GLOBE) program (via Taiwan)]
-
A.
Global Observing System
The Global Observing System is an international network of meteorological and environmental observation platforms that provides essential data for weather forecasting, climate monitoring, and related research worldwide.
-
B.
Earth System Science Programme, The Chinese University of Hong Kong
The Earth System Science Programme at The Chinese University of Hong Kong is an academic unit focused on studying the Earth’s atmosphere, oceans, land, and climate as an integrated system through interdisciplinary science education and research.
-
C.
Global Climate Observing System
The Global Climate Observing System is an international program that coordinates and supports comprehensive, long-term observations of the Earth’s climate system to underpin climate research, services, and policy.
-
D.
Global Science and Engineering Program networks
Global Science and Engineering Program networks is an international consortium that connects universities and institutions to promote collaborative education and research in science and engineering.
-
E.
GEOSS
GEOSS is a global, coordinated system of Earth observation systems designed to provide comprehensive environmental data and information to support science-based decision-making and sustainable development.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Global Learning and Observations to Benefit the Environment (GLOBE) program (via Taiwan) Triple: [National Tsing Hua University, memberOf, Global Learning and Observations to Benefit the Environment (GLOBE) program (via Taiwan)]
Generated description
The Global Learning and Observations to Benefit the Environment (GLOBE) program is an international, school-based science and education initiative that engages students, teachers, and scientists in collaborative environmental data collection and research.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Global Learning and Observations to Benefit the Environment (GLOBE) program (via Taiwan) Target entity description: The Global Learning and Observations to Benefit the Environment (GLOBE) program is an international, school-based science and education initiative that engages students, teachers, and scientists in collaborative environmental data collection and research.
-
A.
Global Observing System
The Global Observing System is an international network of meteorological and environmental observation platforms that provides essential data for weather forecasting, climate monitoring, and related research worldwide.
-
B.
Earth System Science Programme, The Chinese University of Hong Kong
The Earth System Science Programme at The Chinese University of Hong Kong is an academic unit focused on studying the Earth’s atmosphere, oceans, land, and climate as an integrated system through interdisciplinary science education and research.
-
C.
Global Climate Observing System
The Global Climate Observing System is an international program that coordinates and supports comprehensive, long-term observations of the Earth’s climate system to underpin climate research, services, and policy.
-
D.
Global Science and Engineering Program networks
Global Science and Engineering Program networks is an international consortium that connects universities and institutions to promote collaborative education and research in science and engineering.
-
E.
GEOSS
GEOSS is a global, coordinated system of Earth observation systems designed to provide comprehensive environmental data and information to support science-based decision-making and sustainable development.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d81c687b0c819087fd9ed4198403f8 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5ee3213c8190af2853a2a5b302a2 |
completed | April 14, 2026, 3:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcd0a7aab88190949cf1fd8e11b050 |
completed | May 7, 2026, 5:49 p.m. |
| NEDg | Description generation | batch_69fcd5ad82388190a196d811734cdca2 |
completed | May 7, 2026, 6:10 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fcd63a114881909ff7b2df937d24df |
completed | May 7, 2026, 6:13 p.m. |
Created at: April 9, 2026, 10:21 p.m.