Triple
T3016254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | S (historical map designation) |
E82342
|
entity |
| Predicate | mapUsage |
P1987
|
FINISHED |
| Object | historically used on New York City Subway maps |
—
|
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: historically used on New York City Subway maps | Statement: [S (historical map designation), mapUsage, historically used on New York City Subway maps]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mapUsage Context triple: [S (historical map designation), mapUsage, historically used on New York City Subway maps]
-
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.
mapsFrom
Indicates that one entity is derived, transformed, or constructed based on data, structure, or content originating from another entity.
-
C.
mapCoverage
chosen
Indicates the extent or area that is represented, covered, or included by a particular map.
-
D.
mapsTo
Indicates that one entity is associated with or transformed into another entity, typically defining a directional correspondence or function from a source to a target.
-
E.
mapped
Indicates that one entity has been associated, corresponded, or linked systematically to another according to some defined mapping or alignment.
- 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_69ad8b1eb53481908c39bbcd1ec104b2 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9a6c56708190b7d8d08bca727cc1 |
completed | March 8, 2026, 3:49 p.m. |
| PD | Predicate disambiguation | batch_69ad961a97188190809dc73430a8eda8 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3 p.m.