Triple
T723642
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Buttonwood Agreement |
E14672
|
entity |
| Predicate | signatoryCount |
P4946
|
FINISHED |
| Object | 24 |
—
|
LITERAL FINISHED |
How this triple was built (2 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: 24 | Statement: [Buttonwood Agreement, signatoryCount, 24]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: signatoryCount Context triple: [Buttonwood Agreement, signatoryCount, 24]
-
A.
numberOfSignatories
chosen
Indicates the total count of entities that have formally signed or endorsed a given document, agreement, or item.
-
B.
initialSignatoriesCount
Indicates the number of entities that originally signed or agreed to a document, contract, or agreement at its inception.
-
C.
laterSignatoriesCount
Indicates the number of other entities that became signatories after the referenced entity.
-
D.
signatoryBloc
Indicates that an entity is a member of, or aligned with, a specific bloc or group that has jointly signed or endorsed an agreement, treaty, or document.
-
E.
signatoryType
Indicates the specific role or category of a party that has signed or formally agreed to a document, contract, or agreement.
- F. None of above.
Provenance (3 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_69a4934c753c81909b309027e48b9b3a |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a5a5360c8190b16e1e4f4206d0aa |
completed | March 1, 2026, 8:46 p.m. |
| PD | Predicate disambiguation | batch_69a4a4f700cc81908c6de3eedf68433c |
completed | March 1, 2026, 8:43 p.m. |
Created at: March 1, 2026, 7:37 p.m.