Triple
T25333596
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bunopithecus |
E635216
|
entity |
| Predicate | anatomicallySimilarTo |
P133329
|
FINISHED |
| Object | modern gibbons |
—
|
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: modern gibbons | Statement: [Bunopithecus, anatomicallySimilarTo, modern gibbons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: anatomicallySimilarTo Context triple: [Bunopithecus, anatomicallySimilarTo, modern gibbons]
-
A.
materiallySimilarTo
Indicates that two entities share substantially the same physical or material characteristics, composition, or properties, though they may not be exactly identical.
-
B.
homologousTo
Indicates that two entities share a common evolutionary origin or structural similarity, often implying they derive from the same ancestral feature.
-
C.
hasMovementStructureAnalogousTo
Indicates that one entity’s movement structure is similar or functionally analogous to that of another entity.
-
D.
speciesResemblance
chosen
Indicates that one species shares notable similarities in appearance or characteristics with another species.
-
E.
lessSimilarTo
Indicates that one entity is considered to share fewer similarities or a weaker resemblance with another entity compared to some reference or alternative.
- 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_69e75a99bd6481909476115b35b9a8e4 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f497c80e0881908227999fa2c4e0d6 |
completed | May 1, 2026, 12:08 p.m. |
| PD | Predicate disambiguation | batch_69f45d0dbc8c8190beecce679fce90a4 |
completed | May 1, 2026, 7:58 a.m. |
Created at: April 21, 2026, 1:31 p.m.