Triple
T22959701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NHV |
E570858
|
entity |
| Predicate | identifiesFacility |
P150388
|
FINISHED |
| Object | New Haven Union Station platforms |
—
|
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: New Haven Union Station platforms | Statement: [NHV, identifiesFacility, New Haven Union Station platforms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: identifiesFacility Context triple: [NHV, identifiesFacility, New Haven Union Station platforms]
-
A.
isNamedFacilityOf
Indicates that a facility bears the official name associated with a particular entity (such as an organization, person, or place).
-
B.
hasFacilityType
Indicates that an entity possesses or is associated with a specific type or category of facility.
-
C.
isPrimaryFacilityFor
Indicates that one facility serves as the main or principal location responsible for supporting or serving a particular entity or operation.
-
D.
servesFacility
Indicates that one entity provides services or support to a particular facility as its client, target, or area of operation.
-
E.
appliesToFacility
Indicates that something (such as a rule, policy, condition, or attribute) is relevant to, valid for, or in effect at a particular facility.
- F. None of above. chosen
Provenance (4 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_69e245b212a88190b5259caf51606084 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f181f3c96081909abd6ec32103d4c3 |
completed | April 29, 2026, 3:58 a.m. |
| PD | Predicate disambiguation | batch_69ef3b882e708190b0eb0c87021c75b8 |
completed | April 27, 2026, 10:33 a.m. |
| PDg | Predicate description generation | batch_69ef538a115081908982597f79355840 |
completed | April 27, 2026, 12:16 p.m. |
Created at: April 17, 2026, 3:47 p.m.