Triple
T31735936
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Canaan Railroad |
E809992
|
entity |
| Predicate | lineNowKnownAs |
P1213
|
FINISHED |
| Object | New Canaan Branch |
—
|
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 Canaan Branch | Statement: [New Canaan Railroad, lineNowKnownAs, New Canaan Branch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lineNowKnownAs Context triple: [New Canaan Railroad, lineNowKnownAs, New Canaan Branch]
-
A.
centerNowKnownAs
Indicates that a center has changed its name and is currently known by a new name.
-
B.
formerLineName
Indicates that the object is a previous or former name by which the referenced line was known.
-
C.
lineName
Indicates the specific name or designation assigned to a particular line (such as a route, path, or service) that distinguishes it from other lines.
-
D.
knownAsBy
Indicates that one entity is referred to or recognized by another entity using a particular name or designation.
-
E.
currentName
chosen
Indicates the present or most recently assigned name associated with an entity.
- 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_69f348e0e4908190a884582eca646fb7 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6ab23f4608190ace81412a377eff8 |
completed | May 3, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69f6aa20a1588190a53533fc9764efb2 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 30, 2026, 11:23 p.m.