Triple
T375067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Broad Street Station (Philadelphia) |
E8352
|
entity |
| Predicate | closureDate |
P140
|
FINISHED |
| Object | April 27, 1952 |
—
|
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: April 27, 1952 | Statement: [Broad Street Station (Philadelphia), closureDate, April 27, 1952]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: closureDate Context triple: [Broad Street Station (Philadelphia), closureDate, April 27, 1952]
-
A.
closureReason
Indicates the reason or cause for which an entity, process, or case has been closed or terminated.
-
B.
concludedAt
Indicates the point in time at which an event, process, or relationship comes to an end or is completed.
-
C.
closed
Indicates that an entity has brought something (such as an object, container, or space) from an open state into a shut or sealed state, or that it is currently in that shut state.
-
D.
endDate
chosen
Indicates the point in time at which an event, state, or relationship stops being valid or comes to a conclusion.
-
E.
closureAnnouncedBy
Indicates that an entity’s closure has been formally communicated or declared by a specified agent or source.
- 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_69a2e7f2ec648190b42bc7db424f8109 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ec1585648190943f1c698e9b2d81 |
completed | Feb. 28, 2026, 1:22 p.m. |
| PD | Predicate disambiguation | batch_69a2e96216048190873ae533fa5b864d |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.