Triple
T3540826
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bellerophon riding Pegasus |
E74879
|
entity |
| Predicate | typicalAttributesOfHorse |
P48772
|
FINISHED |
| Object | wings |
—
|
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: wings | Statement: [Bellerophon riding Pegasus, typicalAttributesOfHorse, wings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalAttributesOfHorse Context triple: [Bellerophon riding Pegasus, typicalAttributesOfHorse, wings]
-
A.
featuresHorse
Indicates that something includes, presents, or prominently involves a horse as a central element or subject.
-
B.
horseColor
Indicates the relationship that specifies what color a given horse is.
-
C.
firstHorseColor
Indicates the color attribute associated with the first horse in a given context or sequence.
-
D.
acquiredHorsesFrom
Indicates that one entity obtained ownership or control of horses from another entity, typically through purchase, trade, or transfer.
-
E.
secondHorseColor
Indicates that it specifies the color attribute of the second horse in a given context or group.
- F. None of above. chosen
Provenance (4 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_69ad85d274cc8190ab59c97298a1cfbf |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbf729000819086e4fdba9e73e198 |
completed | March 8, 2026, 6:26 p.m. |
| PD | Predicate disambiguation | batch_69adae15749881909b847c6ca73c934e |
completed | March 8, 2026, 5:12 p.m. |
| PDg | Predicate description generation | batch_69adb0a11a1c8190baa8c0eb87ad259a |
completed | March 8, 2026, 5:23 p.m. |
Created at: March 8, 2026, 3:20 p.m.