Triple
T5576471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chevrolet Bel Air (top trim) |
E146330
|
entity |
| Predicate | becameSeparateSeries |
P12384
|
FINISHED |
| Object | 1953 model year |
—
|
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: 1953 model year | Statement: [Chevrolet Bel Air (top trim), becameSeparateSeries, 1953 model year]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: becameSeparateSeries Context triple: [Chevrolet Bel Air (top trim), becameSeparateSeries, 1953 model year]
-
A.
separatedInto
Indicates that something has been divided or split into distinct parts, groups, or components.
-
B.
establishedAsSeparateTitle
chosen
Indicates that something has been formally created or recognized as an independent, distinct title separate from a previous or parent title.
-
C.
separateCrownSince
Indicates that one entity has had a distinct or independent crown (monarchy) from another entity since a specified point in time.
-
D.
releaseSeries
Indicates that one entity publishes or makes available a sequence of related releases (such as episodes, issues, or installments) as part of an ongoing series.
-
E.
isSeriesOf
Indicates that one entity is a sequence or set of related items that collectively form a series 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_69c008ffed108190a084602227af6157 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c020697fbc8190bd084d7896db3ab8 |
completed | March 22, 2026, 5:01 p.m. |
| PD | Predicate disambiguation | batch_69c01b147cc081909237f3f2967d4cb8 |
completed | March 22, 2026, 4:38 p.m. |
Created at: March 22, 2026, 3:37 p.m.