Triple
T23097976
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 68th Street–Hunter College station |
E575945
|
entity |
| Predicate | mapIdentifier |
P13793
|
FINISHED |
| Object | NYCS map 68th Street–Hunter College |
—
|
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: NYCS map 68th Street–Hunter College | Statement: [68th Street–Hunter College station, mapIdentifier, NYCS map 68th Street–Hunter College]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mapIdentifier Context triple: [68th Street–Hunter College station, mapIdentifier, NYCS map 68th Street–Hunter College]
-
A.
mapNumber
Indicates a correspondence where each element in one set or collection is assigned a specific numeric value in another set or domain.
-
B.
mapLabel
chosen
Indicates that a label or name is assigned to a map or mapped entity for identification or display.
-
C.
mapSystem
Indicates a relationship where one system is associated with or represented by a specific map or mapping framework.
-
D.
mapsFrom
Indicates that one entity is derived, transformed, or constructed based on data, structure, or content originating from another entity.
-
E.
mapsAs
Indicates that one entity serves as a mapping or correspondence to another, typically translating or associating elements from one domain or representation to another.
- 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_69e245c060b48190a9bd61a47a16db17 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18de61c7c8190809920fa1071935f |
completed | April 29, 2026, 4:49 a.m. |
| PD | Predicate disambiguation | batch_69ef89e5ce748190b2c3ac3843484127 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:57 p.m.