Triple
T27085081
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2001 New York City mayoral election |
E686014
|
entity |
| Predicate | successorMayor |
P155423
|
FINISHED |
| Object | Michael Bloomberg |
—
|
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: Michael Bloomberg | Statement: [2001 New York City mayoral election, successorMayor, Michael Bloomberg]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorMayor Context triple: [2001 New York City mayoral election, successorMayor, Michael Bloomberg]
-
A.
successorOfficeHolder
Indicates that one office holder directly follows another in occupying the same official position.
-
B.
successorAsChief
Indicates that one entity becomes the next chief, taking over the leadership role from another entity.
-
C.
succeededBy (Mayor of New York City)
chosen
Indicates that one individual directly follows another in holding the position of Mayor of New York City.
-
D.
formerMayor
Indicates that the subject once held the position of mayor of the object entity but no longer does.
-
E.
wonMayoraltyOf
Indicates that one entity won the election to become mayor of a specified place or jurisdiction.
- 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_69ef148940ec819097b5c20fbfbf7c81 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f78c61ed4c8190ad84c918fa9af55a |
completed | May 3, 2026, 5:56 p.m. |
| PD | Predicate disambiguation | batch_69f78b8cb3a881909ebaac1b503988c2 |
completed | May 3, 2026, 5:53 p.m. |
Created at: April 27, 2026, 8:37 a.m.