Triple
T3984483
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BMT Broadway Line |
E86837
|
entity |
| Predicate | trunkRole |
P6821
|
FINISHED |
| Object | Manhattan trunk line for BMT services |
—
|
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: Manhattan trunk line for BMT services | Statement: [BMT Broadway Line, trunkRole, Manhattan trunk line for BMT services]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trunkRole Context triple: [BMT Broadway Line, trunkRole, Manhattan trunk line for BMT services]
-
A.
trunkCharacteristic
Indicates a relationship where a specific characteristic or property is attributed to a trunk (such as that of a tree or similar object).
-
B.
hasTrunk
Indicates that one entity possesses or is equipped with a trunk as a physical feature or component.
-
C.
transportationRole
chosen
Indicates a role or function that an entity has specifically in the context of providing, operating, or supporting transportation.
-
D.
transportRole
Indicates that an entity participates in a transportation process with a specific functional role (e.g., carrier, passenger, cargo, or operator).
-
E.
trackRole
Indicates that an entity holds or performs a specific role within the context of a particular track or sequence of 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_69aed93fd9d4819085d3b2137d2346cb |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefa3ef7ac8190abe02f440ff83c43 |
completed | March 9, 2026, 4:50 p.m. |
| PD | Predicate disambiguation | batch_69aef8f492ac819089dbb9436dbcdd2b |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:33 p.m.