Triple
T36392914
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Union Street |
E896376
|
entity |
| Predicate | expressTracksUsage |
P117004
|
FINISHED |
| Object | N and W trains (peak and late night patterns) |
—
|
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: N and W trains (peak and late night patterns) | Statement: [Union Street, expressTracksUsage, N and W trains (peak and late night patterns)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: expressTracksUsage Context triple: [Union Street, expressTracksUsage, N and W trains (peak and late night patterns)]
-
A.
tracksUsage
Indicates that one entity monitors, records, or keeps a log of how another entity is used over time.
-
B.
trackUsage
Indicates that one entity monitors and records how another entity or resource is being used over time.
-
C.
trackUsed
Indicates that a particular track (such as a route, path, or media track) has been utilized or selected in a given context.
-
D.
expressTracksBypass
chosen
Indicates that express train tracks pass around or avoid a particular location or section rather than going directly through it.
-
E.
usesTestTrack
Indicates that one entity makes use of a specific test track for testing, evaluation, or validation activities.
- 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_69f76e52e3108190becf70b090ae7bd6 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7be9d07ac8190adf796cbef60daf6 |
completed | May 3, 2026, 9:31 p.m. |
| PD | Predicate disambiguation | batch_69f7bcccd7988190aa5c931ff347d33c |
completed | May 3, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:10 p.m.