Triple
T24556085
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvey Bullock |
E607519
|
entity |
| Predicate | oftenPartnerOf |
P82864
|
FINISHED |
| Object | James Gordon |
—
|
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: James Gordon | Statement: [Harvey Bullock, oftenPartnerOf, James Gordon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oftenPartnerOf Context triple: [Harvey Bullock, oftenPartnerOf, James Gordon]
-
A.
partnerInActWith
chosen
Indicates that two or more entities jointly participate as partners in carrying out the same act or action.
-
B.
partnerInUnionWith
Indicates a mutual partnership or union relationship between two entities, such as a civil, domestic, or similar legally or socially recognized union.
-
C.
symbolicPartnerOf
Indicates a relationship in which two entities are formally or representationally associated as partners in a symbolic, rather than practical or operational, sense.
-
D.
laterPartnerInPracticeWith
Indicates that one entity became a partner in professional practice with another entity at a later point in time.
-
E.
accompaniesTo
Indicates that one entity goes along with or escorts another entity to a specific destination or event.
- 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_69e2c4cae1b88190825e88d5ce8aa61e |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2a8f2af7c8190904f247ef29121d0 |
completed | April 30, 2026, 12:57 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b99e7c8190ba7e2dc8729a314a |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:27 a.m.