Triple
T23934150
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lanyu Nuclear Waste Storage Facility |
E602584
|
entity |
| Predicate | storesWasteFrom |
P104206
|
FINISHED |
| Object |
Taiwan nuclear power plants
Taiwan nuclear power plants are a set of commercial nuclear power-generating facilities in Taiwan that have supplied a significant portion of the island’s electricity while being central to its energy and environmental policy debates.
|
E1610922
|
NE FINISHED |
How this triple was built (3 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: Taiwan nuclear power plants | Statement: [Lanyu Nuclear Waste Storage Facility, storesWasteFrom, Taiwan nuclear power plants]
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: Taiwan nuclear power plants Triple: [Lanyu Nuclear Waste Storage Facility, storesWasteFrom, Taiwan nuclear power plants]
Generated description
Taiwan nuclear power plants are a set of commercial nuclear power-generating facilities in Taiwan that have supplied a significant portion of the island’s electricity while being central to its energy and environmental policy debates.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: storesWasteFrom Context triple: [Lanyu Nuclear Waste Storage Facility, storesWasteFrom, Taiwan nuclear power plants]
-
A.
containsWasteFrom
chosen
Indicates that one entity holds, includes, or is contaminated by waste originating from another entity.
-
B.
wasteOrigin
Indicates that one entity is the original source or point of generation of a particular waste associated with another entity.
-
C.
typeOfWasteCovered
Indicates the specific category or kind of waste material that is included or addressed within a given context, agreement, or regulation.
-
D.
wasteManagement
Indicates the handling, treatment, and disposal relationship between entities and the waste materials they produce or manage.
-
E.
wasteManagementFacility
Indicates a facility where waste materials are collected, processed, treated, or disposed of as part of a waste management system.
- F. None of above.
Provenance (6 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_69e2953cf6e081909b8e25a10a52dddc |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1cf9da9c4819085880c6ad521d7ed |
completed | April 29, 2026, 9:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0f764728e88190b084674692ca2002 |
completed | May 21, 2026, 9:16 p.m. |
| NEDg | Description generation | batch_6a0f76f2b5248190b92095f8003001be |
completed | May 21, 2026, 9:19 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0f78df8c9c81908eb3912b212862f9 |
completed | May 21, 2026, 9:27 p.m. |
| PD | Predicate disambiguation | batch_69f16151ebdc819086e9e1d7cc1f4f3c |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:59 p.m.