Triple
T26148993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fairfield, Connecticut |
E659759
|
entity |
| Predicate | isServedByRailLine |
P154206
|
FINISHED |
| Object | New Haven Line |
—
|
NE NERFINISHED |
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 Line | Statement: [Fairfield, Connecticut, isServedByRailLine, New Haven Line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isServedByRailLine Context triple: [Fairfield, Connecticut, isServedByRailLine, New Haven Line]
-
A.
hasRailServiceAt
chosen
Indicates that a rail transport service operates at or serves a particular location or facility.
-
B.
isRailServiceOf
Indicates that a particular rail service operates for, belongs to, or is provided by a specified entity (such as a route, operator, or network).
-
C.
railwayTypeServed
Indicates the type of railway system or service that a given entity (such as a station, line, or facility) is designed to serve or accommodate.
-
D.
servesCommuterRailLine
Indicates that a location or facility provides access to and is a stop or station for a commuter rail line.
-
E.
hasRailRoute
Indicates that there exists a rail-based transportation route or connection between the related entities.
- 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_69ee5bc496a88190af7deb7ab5e081de |
completed | April 26, 2026, 6:39 p.m. |
| NER | Named-entity recognition | batch_69f60bea4cc8819080c1785709c275cb |
completed | May 2, 2026, 2:36 p.m. |
| PD | Predicate disambiguation | batch_69f5f7fd90fc81909055b211368f9139 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 8:24 p.m.