Triple
T24119396
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rhinolophidae |
E597608
|
entity |
| Predicate | echolocationCall |
P28101
|
FINISHED |
| Object | constant-frequency calls |
—
|
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: constant-frequency calls | Statement: [Rhinolophidae, echolocationCall, constant-frequency calls]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: echolocationCall Context triple: [Rhinolophidae, echolocationCall, constant-frequency calls]
-
A.
usesEcholocation
chosen
Indicates that an entity employs echolocation, using reflected sound waves to detect, locate, or navigate around objects or other entities.
-
B.
usesElectroreceptionFor
Indicates that an entity detects and interprets electrical fields in its environment specifically for the associated purpose or activity.
-
C.
breedingCall
Indicates that one entity produces a vocalization or signal intended to attract a mate or initiate reproductive behavior with another entity.
-
D.
canHear
Indicates that one entity is able to perceive sounds produced by another entity.
-
E.
soundHeardDistanceApproximate
Indicates that a sound was heard at an estimated, not precisely measured, distance from the listener or reference point.
- 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_69e288c74200819098ab875b592cb39f |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1dee1a2608190870ade02495c5ebe |
completed | April 29, 2026, 10:35 a.m. |
| PD | Predicate disambiguation | batch_69f1765650fc8190a6bc1eb512b240bf |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11:05 p.m.