Triple
T5501697
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Railfreight |
E144342
|
entity |
| Predicate | usedLivery |
P21786
|
FINISHED |
| Object | Railfreight grey livery with sector decals |
—
|
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: Railfreight grey livery with sector decals | Statement: [Railfreight, usedLivery, Railfreight grey livery with sector decals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedLivery Context triple: [Railfreight, usedLivery, Railfreight grey livery with sector decals]
-
A.
hasLivery
chosen
Indicates that one entity bears or displays the distinctive colors, markings, or branding (livery) associated with another entity.
-
B.
liveryFeature
Indicates a characteristic or design element that is part of a specific livery or external appearance scheme.
-
C.
liveryColors
Indicates the specific set of colors used as the official or characteristic color scheme associated with an entity (such as a brand, organization, or vehicle).
-
D.
usedBrand
Indicates that an entity has utilized, applied, or operated a particular brand in some context.
-
E.
usedStyle
Indicates that one entity employed or applied a particular style, method, or manner associated with 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_69c008f5a2748190bce7a39aabf87a6d |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c01f0a512c81908f077378917e5879 |
completed | March 22, 2026, 4:55 p.m. |
| PD | Predicate disambiguation | batch_69c01b052f3c81909f71c6add0f35a6f |
completed | March 22, 2026, 4:38 p.m. |
Created at: March 22, 2026, 3:32 p.m.