Triple
T20844955
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deinonychus |
E513195
|
entity |
| Predicate | possibleFeatherCovering |
P80642
|
FINISHED |
| Object | inferred from close relatives |
—
|
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: inferred from close relatives | Statement: [Deinonychus, possibleFeatherCovering, inferred from close relatives]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: possibleFeatherCovering Context triple: [Deinonychus, possibleFeatherCovering, inferred from close relatives]
-
A.
numberOfFeathers
Indicates the specific count of feathers associated with an entity.
-
B.
plumageFeature
Indicates a relationship where a specific characteristic or attribute is associated with an entity’s plumage (feathers).
-
C.
featherTypeIndicates
Indicates that a particular type or characteristic of feathers signifies or conveys information about another property, status, or classification of the entity.
-
D.
hasFeatheredMembers
chosen
Indicates that at least some members of a group or category possess feathers.
-
E.
hasWingsMadeOf
Indicates that one entity has wings whose material or composition is made from the other 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_69e0b4f4898081908209e58edb8f9c45 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c34deef88190992b959b83bc59b1 |
completed | April 21, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69e5c9a1f4f48190aa9fb4ef8f8aea5a |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:43 p.m.