Triple
T5771658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trochilidae |
E127342
|
entity |
| Predicate | wingBeatFrequency |
P66325
|
FINISHED |
| Object | very high relative to body size |
—
|
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: very high relative to body size | Statement: [Trochilidae, wingBeatFrequency, very high relative to body size]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wingBeatFrequency Context triple: [Trochilidae, wingBeatFrequency, very high relative to body size]
-
A.
typeOfWing
Indicates the specific kind or category of wing that an entity possesses or is associated with.
-
B.
fliesAbove
Indicates that one entity moves through the air at a higher altitude than another entity, passing over it in space.
-
C.
hasWings
Indicates that an entity possesses wings as physical appendages.
-
D.
fliesOn
Indicates that an entity travels as a passenger or cargo aboard a particular aircraft, airline, or flight.
-
E.
fly
Indicates movement through the air, typically by using wings or an aircraft, from one location to another.
- 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_69c00834f6308190851b0abeddd8ed7e |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c02acb12c081908e4beee4a957f9f9 |
completed | March 22, 2026, 5:45 p.m. |
| PD | Predicate disambiguation | batch_69c021ce8d3c81909b332cb1c33a61ad |
completed | March 22, 2026, 5:07 p.m. |
| PDg | Predicate description generation | batch_69c02ac9603481909e3fa295d7904a15 |
completed | March 22, 2026, 5:45 p.m. |
Created at: March 22, 2026, 3:50 p.m.