Triple
T37221312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Green Car |
E922888
|
entity |
| Predicate | locationOnTrain |
P131997
|
FINISHED |
| Object | designated Green Car coaches |
—
|
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: designated Green Car coaches | Statement: [Green Car, locationOnTrain, designated Green Car coaches]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationOnTrain Context triple: [Green Car, locationOnTrain, designated Green Car coaches]
-
A.
positionInTrain
chosen
Indicates the relative location or ordering of an entity within the sequence of cars or sections that make up a train.
-
B.
isOnRailway
Indicates that one entity is positioned on, aligned with, or traveling along a railway track or railway system in relation to another entity.
-
C.
railPortalLocation
Indicates the geographic location or position of a rail portal (such as a tunnel or access point) relative to other referenced entities.
-
D.
trainsOn
Indicates that one entity receives training, instruction, or practice using or based on another entity (such as a resource, dataset, tool, or subject).
-
E.
seatLocatedIn
Indicates that a seat is situated within or belongs to a specific location or area.
- 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_69f76ea6f5288190b8d9988f613811c0 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a11efc08190bb7cacc1325b4dc6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:15 p.m.