Triple
T309325
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mercury |
E6367
|
entity |
| Predicate | notableBodyStyle |
P8243
|
FINISHED |
| Object | full-size sedans |
—
|
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: full-size sedans | Statement: [Mercury, notableBodyStyle, full-size sedans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableBodyStyle Context triple: [Mercury, notableBodyStyle, full-size sedans]
-
A.
primaryBodyStyle
chosen
Indicates the main or predominant body configuration or structural form associated with an entity.
-
B.
notableText
Indicates that a particular piece of text is especially significant, prominent, or worthy of attention in relation to the associated entity or context.
-
C.
notableFor
Indicates that an entity is especially recognized or distinguished for a particular quality, achievement, characteristic, or role.
-
D.
notableElement
Indicates that an entity has a component, feature, or part that is especially significant, prominent, or noteworthy in relation to it.
-
E.
notableStandard
Indicates that one entity is a widely recognized or influential standard that the other entity is associated with or exemplifies.
- 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_69a2e79230508190b912ecb555aae17e |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2ea33ba688190b30d285cd7aa0d82 |
completed | Feb. 28, 2026, 1:14 p.m. |
| PD | Predicate disambiguation | batch_69a2e93f38308190b4b480c951f1a1c3 |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:06 p.m.