Triple
T31589508
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York Central Putnam Division |
E806050
|
entity |
| Predicate | passengerServiceEndDate |
P101820
|
FINISHED |
| Object | 1958 |
—
|
LITERAL FINISHED |
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: 1958 | Statement: [New York Central Putnam Division, passengerServiceEndDate, 1958]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: passengerServiceEndDate Context triple: [New York Central Putnam Division, passengerServiceEndDate, 1958]
-
A.
airportPassengerServiceEndedAt
Indicates that the provision of passenger-related services at an airport concluded at a specific time or event.
-
B.
holderEndDate
Indicates the date on which an entity’s role as holder of something (e.g., an asset, position, or right) comes to an end.
-
C.
notableFlightEndDate
Indicates the date on which a notable or significant flight concluded or reached its endpoint.
-
D.
cessationDate
chosen
Indicates the date on which an ongoing state, activity, or relationship comes to an end.
-
E.
typicallyEndsAt
Indicates that an event, process, or activity most commonly or usually concludes at a particular time, place, or state.
- 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_69f348d4891c8190b02bae3c8ecb68b7 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f71996e1a48190ac59a1d66d7c44e8 |
completed | May 3, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69f71820c6c88190ab38b4fa626d22cc |
completed | May 3, 2026, 9:40 a.m. |
Created at: April 30, 2026, 10:27 p.m.