Triple
T36978278
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pilot Metropolitan |
E914754
|
entity |
| Predicate | trimColorOptions |
P14111
|
FINISHED |
| Object | various finishes depending on model line |
—
|
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: various finishes depending on model line | Statement: [Pilot Metropolitan, trimColorOptions, various finishes depending on model line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trimColorOptions Context triple: [Pilot Metropolitan, trimColorOptions, various finishes depending on model line]
-
A.
hasColorOption
chosen
Indicates that an entity offers or supports a particular color as one of its selectable options.
-
B.
tieColor
Indicates the color attribute associated with a tie worn or possessed by an entity.
-
C.
hoodColor
Indicates the color attribute specifically of an entity’s hood (e.g., the hood of a garment or vehicle).
-
D.
colorSelection
Indicates the relationship in which an entity chooses or is assigned a specific color from a set of possible colors.
-
E.
laterColorOption
Indicates that one color option occurs or becomes available after another in a sequence or ordering.
- 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_69f76e8d13b4819089af24a47ce092fc |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb154c0fe08190a2e41e7a29b6055f |
completed | May 6, 2026, 10:17 a.m. |
| PD | Predicate disambiguation | batch_69f9fecc005c8190be082a8689193745 |
completed | May 5, 2026, 2:29 p.m. |
Created at: May 3, 2026, 4:14 p.m.