Triple
T155140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Francisco Conference |
E3162
|
entity |
| Predicate | legalStatusOfOutcome |
P2250
|
FINISHED |
| Object | multilateral treaty |
—
|
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: multilateral treaty | Statement: [San Francisco Conference, legalStatusOfOutcome, multilateral treaty]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legalStatusOfOutcome Context triple: [San Francisco Conference, legalStatusOfOutcome, multilateral treaty]
-
A.
legalOutcome
Indicates the resulting legal status, decision, or consequence that follows from a legal process, action, or judgment.
-
B.
hasLegalStatus
chosen
Indicates that an entity possesses a particular legal classification, recognition, or standing under law.
-
C.
finalDisposition
Indicates the ultimate outcome, status, or resolution assigned to an entity after all relevant processes or decisions are complete.
-
D.
status
Indicates the current condition, state, or standing of an entity within a given context.
-
E.
deFactoStatus
Indicates that one entity holds a role, position, or status in practice or by custom, even if it is not formally or legally recognized.
- 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_69a2527757ec819090b8becb2cf1a862 |
completed | Feb. 28, 2026, 2:27 a.m. |
| NER | Named-entity recognition | batch_69a258e0b11c8190b7b5cf3c354c47ce |
completed | Feb. 28, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69a2565c727c8190bca9ba6ca52f216a |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:31 a.m.