Triple
T29132662
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lexington Avenue between 25th and 26th Streets |
E738420
|
entity |
| Predicate | eventStartDateAtSite |
P46342
|
FINISHED |
| Object | 1913-02-17 |
—
|
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: 1913-02-17 | Statement: [Lexington Avenue between 25th and 26th Streets, eventStartDateAtSite, 1913-02-17]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eventStartDateAtSite Context triple: [Lexington Avenue between 25th and 26th Streets, eventStartDateAtSite, 1913-02-17]
-
A.
eventStartDateOrganized
chosen
Indicates the date on which an event is formally scheduled or organized to begin.
-
B.
eventDateAtLocation
Indicates that a specific event occurs on a particular date at a given location.
-
C.
eventOccurredAt
Indicates that a particular event took place at a specific time or location.
-
D.
eventDateContext
Indicates the contextual role or significance that a specific date has within an event (e.g., whether it is the start, end, deadline, or another relevant temporal marker).
-
E.
startsAt
Indicates that an event, process, or state begins at a specific time, location, or point in a sequence.
- 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_69f07cb3adb48190a9e0e169cd026634 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f68a16debc8190a12f5f65ced055d7 |
completed | May 2, 2026, 11:34 p.m. |
| PD | Predicate disambiguation | batch_69f6860def1c81909d79e1f088c4b5e5 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 28, 2026, 11:32 a.m.