Triple
T54449
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amtrak |
E1072
|
entity |
| Predicate | offersServiceClass |
P849
|
FINISHED |
| Object | Coach |
—
|
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: Coach | Statement: [Amtrak, offersServiceClass, Coach]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offersServiceClass Context triple: [Amtrak, offersServiceClass, Coach]
-
A.
offersActivity
Indicates that one entity provides or makes available a specific activity for another entity to participate in or use.
-
B.
offersProgram
Indicates that an entity provides or makes available a specific program (such as a course, curriculum, or initiative).
-
C.
hasServiceType
chosen
Indicates that an entity is associated with or categorized by a particular type of service.
-
D.
offersProgramLevel
Indicates that an entity provides or makes available an academic or training program at a specified level (e.g., undergraduate, graduate, certificate).
-
E.
availableAs
Indicates that one entity can be used, accessed, or offered in the form, role, or capacity of another 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_69a248adc5b48190aa8db9fb092fb28a |
completed | Feb. 28, 2026, 1:45 a.m. |
| NER | Named-entity recognition | batch_69a24b3a9e848190b80de3c858678b3a |
completed | Feb. 28, 2026, 1:56 a.m. |
| PD | Predicate disambiguation | batch_69a24ac52fb08190aa7c38f83434f795 |
completed | Feb. 28, 2026, 1:54 a.m. |
Created at: Feb. 28, 2026, 1:50 a.m.