Triple
T6323096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MBTA paratransit service |
E141791
|
entity |
| Predicate | serviceRelationship |
P12758
|
FINISHED |
| Object | complements MBTA fixed-route transit |
—
|
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: complements MBTA fixed-route transit | Statement: [MBTA paratransit service, serviceRelationship, complements MBTA fixed-route transit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: serviceRelationship Context triple: [MBTA paratransit service, serviceRelationship, complements MBTA fixed-route transit]
-
A.
relatedService
chosen
Indicates that one service is connected or associated with another service in a relevant or dependent way.
-
B.
reportsRelationship
Indicates that one entity formally provides information, findings, or status about another entity or situation.
-
C.
identityRelation
Indicates that two entities are in fact the very same entity, not merely similar or equivalent.
-
D.
relationshipType
Indicates the specific kind of relationship that exists between two or more entities.
-
E.
employerRelationship
Indicates a relationship in which one entity acts as the employer of another, having authority to hire, direct, and compensate the other party for work performed.
- 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_69c008d201748190917e69c41ba3f978 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c064e38f1c81909c7e90b520602bae |
completed | March 22, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69c060e5efc48190861b8266e5b0cc0c |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:29 p.m.