Triple
T18632782
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ant chair |
E455463
|
entity |
| Predicate | backrestShapeInspiration |
P14113
|
FINISHED |
| Object | ant with its head raised |
—
|
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: ant with its head raised | Statement: [Ant chair, backrestShapeInspiration, ant with its head raised]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: backrestShapeInspiration Context triple: [Ant chair, backrestShapeInspiration, ant with its head raised]
-
A.
hasBackrestType
chosen
Indicates the specific kind or style of backrest that an object (typically a seat or chair) possesses.
-
B.
hasBackrest
Indicates that one entity (typically a seat or seating object) includes or is equipped with a supporting backrest.
-
C.
backSupport
Indicates that one entity provides physical or structural support to the back of another entity.
-
D.
architecturalStyleOfSeat
Indicates the architectural style that characterizes a particular seat or seating structure.
-
E.
cushionSupport
Indicates that one entity provides a soft, stabilizing, or protective support to another, often by absorbing impact or pressure.
- 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_69d8d38cc7948190a55ea64e5638994e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e54fc5c7ec8190ab0c64f009583f96 |
completed | April 19, 2026, 9:57 p.m. |
| PD | Predicate disambiguation | batch_69e478d4a7948190a4bb9223bb5dddfc |
completed | April 19, 2026, 6:40 a.m. |
Created at: April 10, 2026, 11:46 a.m.