Triple
T27250570
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1989 New York City mayoral election |
E687473
|
entity |
| Predicate | primaryElectionLoser |
P98823
|
FINISHED |
| Object | Ed Koch |
—
|
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: Ed Koch | Statement: [1989 New York City mayoral election, primaryElectionLoser, Ed Koch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryElectionLoser Context triple: [1989 New York City mayoral election, primaryElectionLoser, Ed Koch]
-
A.
democraticPrimaryLoser
chosen
Indicates that an entity is a candidate who participated in a Democratic primary election and did not win that primary.
-
B.
incumbentLostPrimaryTo
Indicates that a current officeholder was defeated by a challenger in their party’s primary election.
-
C.
popularVoteLoser
Indicates that the subject became the winner of an election despite receiving fewer popular votes than at least one opponent.
-
D.
primaryElection
Indicates a relationship where an election is held within a party or jurisdiction to select its main candidate(s) for a subsequent general or higher-level election.
-
E.
lostPresidentialElection
Indicates that a candidate participated in a presidential election and was defeated rather than elected president.
- 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_69ef35567e808190a94458cd44ebff0c |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69ff255b84788190a94682f4efe1d0b8 |
completed | May 9, 2026, 12:15 p.m. |
| PD | Predicate disambiguation | batch_69ff24f3ab108190bb017a656cff3d82 |
completed | May 9, 2026, 12:13 p.m. |
Created at: April 27, 2026, 10:45 a.m.