Triple
T5489970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gulf of Maine Research Institute |
E123676
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object |
GMRI
GMRI is a nonprofit marine science and education organization focused on studying and sustaining the Gulf of Maine ecosystem.
|
E522548
|
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: GMRI | Statement: [Gulf of Maine Research Institute, abbreviation, GMRI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GMRI Context triple: [Gulf of Maine Research Institute, abbreviation, GMRI]
-
A.
GMRC
GMRC is the organization responsible for developing and operating the metro rail system in Ahmedabad, India.
-
B.
GCI
GCI is the Getty Conservation Institute, a research and education organization dedicated to advancing the conservation of cultural heritage worldwide.
-
C.
GMMS
GMMS is the National Location Code used within the UK rail industry to uniquely identify Mills Hill railway station in operational and ticketing systems.
-
D.
GBI
GBI was the abbreviated name for the General Building Inspector for the Reich Capital, a Nazi-era office responsible for overseeing large-scale architectural and urban redevelopment projects in Berlin.
-
E.
GWI
GWI is the National Rail station code for Greenwich railway station in London, England.
- 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: GMRI Triple: [Gulf of Maine Research Institute, abbreviation, GMRI]
Generated description
GMRI is a nonprofit marine science and education organization focused on studying and sustaining the Gulf of Maine ecosystem.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: GMRI Target entity description: GMRI is a nonprofit marine science and education organization focused on studying and sustaining the Gulf of Maine ecosystem.
-
A.
GMRC
GMRC is the organization responsible for developing and operating the metro rail system in Ahmedabad, India.
-
B.
GCI
GCI is the Getty Conservation Institute, a research and education organization dedicated to advancing the conservation of cultural heritage worldwide.
-
C.
GMMS
GMMS is the National Location Code used within the UK rail industry to uniquely identify Mills Hill railway station in operational and ticketing systems.
-
D.
GBI
GBI was the abbreviated name for the General Building Inspector for the Reich Capital, a Nazi-era office responsible for overseeing large-scale architectural and urban redevelopment projects in Berlin.
-
E.
GWI
GWI is the National Rail station code for Greenwich railway station in London, England.
- 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_69bd464a2d908190869324ce176779c8 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd927dcb848190a9d31e2435f8a755 |
completed | March 20, 2026, 6:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf48ac6e7881908806f88056409b41 |
completed | March 22, 2026, 1:41 a.m. |
| NEDg | Description generation | batch_69bf497a88b48190b87bf175fe224211 |
completed | March 22, 2026, 1:44 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69bf4a1f6e1c8190a9ae94e45fb16cf9 |
completed | March 22, 2026, 1:47 a.m. |
Created at: March 20, 2026, 2:10 p.m.