Triple
T155103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Francisco Conference |
E3162
|
entity |
| Predicate | numberOfParticipatingStates |
P1590
|
FINISHED |
| Object | 50 |
—
|
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: 50 | Statement: [San Francisco Conference, numberOfParticipatingStates, 50]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfParticipatingStates Context triple: [San Francisco Conference, numberOfParticipatingStates, 50]
-
A.
numberOfStates
Indicates the total count of distinct states or conditions associated with an entity or system.
-
B.
numberOfMemberStates
chosen
Indicates the total count of member states associated with a given entity or organization.
-
C.
hasMembersPerState
Indicates a relationship that specifies how many members are associated with each state.
-
D.
numberOfStatesParties
Indicates the total count of entities that are formally parties to a given agreement, treaty, or arrangement.
-
E.
conventionState
Indicates that an entity is in a particular formal status or phase within a convention or agreed procedural framework.
- 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.