Triple
T36488915
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2.5D sketch |
E899003
|
entity |
| Predicate | doesNotFullySpecify |
P7053
|
FINISHED |
| Object | object-centered shape |
—
|
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: object-centered shape | Statement: [2.5D sketch, doesNotFullySpecify, object-centered shape]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: doesNotFullySpecify Context triple: [2.5D sketch, doesNotFullySpecify, object-centered shape]
-
A.
doesNotSpecify
chosen
Indicates that the subject intentionally leaves some information, detail, or attribute undefined or unspecified with respect to the object.
-
B.
doesNotFullyExplain
Indicates that one entity’s explanation of another entity, event, or situation is incomplete or insufficient to account for it fully.
-
C.
doesNotDefine
Indicates that one entity does not provide a definition, specification, or determining description for another entity.
-
D.
doesNotDetermine
Indicates that one entity or factor does not uniquely fix, decide, or specify the state, value, or outcome of another.
-
E.
doesNotComplyWith
Indicates that one entity fails to meet, follow, or adhere to the rules, standards, or requirements set by another entity or authority.
- 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_69f76e5ad4588190bdbce60c52fbb785 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c777e924819081a6634f549fe552 |
completed | May 3, 2026, 10:08 p.m. |
| PD | Predicate disambiguation | batch_69f7c477a4d481908f52e55b6688f60c |
completed | May 3, 2026, 9:56 p.m. |
Created at: May 3, 2026, 4:10 p.m.