Triple
T24293608
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Lindsay |
E605889
|
entity |
| Predicate | residenceWhileMayor |
P34202
|
FINISHED |
| Object | Gracie Mansion |
—
|
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: Gracie Mansion | Statement: [John Lindsay, residenceWhileMayor, Gracie Mansion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: residenceWhileMayor Context triple: [John Lindsay, residenceWhileMayor, Gracie Mansion]
-
A.
residenceWhileInOffice
chosen
Indicates the place where a person lives or is officially resident during the period they hold a particular office or position.
-
B.
cityDuringTenure
Indicates the city in which an entity was located or served during a specified person’s tenure in a role or position.
-
C.
startTimeAsMayoralResidence
Indicates the point in time when a location first began to serve as a mayoral residence.
-
D.
numberOfTermsAsMayor
Indicates the number of distinct terms an individual has served in the role of mayor.
-
E.
termEndAsMayor
Indicates that an entity’s period of service in the role of mayor has concluded at a specified time 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_69e29549335881909cbf27adcaba1cf0 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f2915870c8819089c14de19ba2a5c5 |
completed | April 29, 2026, 11:16 p.m. |
| PD | Predicate disambiguation | batch_69f1c45c6ec081908401b69424428100 |
completed | April 29, 2026, 8:42 a.m. |
Created at: April 18, 2026, 12:09 a.m.