Triple
T5208939
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York Produce Exchange (consulting work) |
E117581
|
entity |
| Predicate | hasConsultant |
P13956
|
FINISHED |
| Object | Leopold Eidlitz |
—
|
NE NERFINISHED |
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: Leopold Eidlitz | Statement: [New York Produce Exchange (consulting work), hasConsultant, Leopold Eidlitz]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasConsultant Context triple: [New York Produce Exchange (consulting work), hasConsultant, Leopold Eidlitz]
-
A.
hasCounsel
Indicates that one entity serves as a legal advisor or representative (counsel) for another entity.
-
B.
consulted
Indicates that one entity sought advice, information, or guidance from another entity.
-
C.
consultsOn
chosen
Indicates that one entity provides expert advice, guidance, or professional input to another entity regarding a specific subject, project, or decision.
-
D.
hasAppointer
Indicates that one entity is responsible for appointing or assigning another entity to a role, position, or function.
-
E.
hasStakeholder
Indicates that an entity is a stakeholder of another entity, typically having an interest, involvement, or influence in its activities or outcomes.
- 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_69bd4464ba3c8190bc16b2ebbe42ddb0 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7a6f0ffc819090b8b59fc22f4dae |
completed | March 20, 2026, 4:48 p.m. |
| PD | Predicate disambiguation | batch_69bd77bb4e8c819094b5ac7cf61512f9 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:47 p.m.