Triple
T17879048
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | little spotted kiwi |
E447031
|
entity |
| Predicate | hasDistinctiveCall |
P82216
|
FINISHED |
| Object | high-pitched whistle |
—
|
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: high-pitched whistle | Statement: [little spotted kiwi, hasDistinctiveCall, high-pitched whistle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDistinctiveCall Context triple: [little spotted kiwi, hasDistinctiveCall, high-pitched whistle]
-
A.
hasCatchySound
Indicates that something possesses an appealing, memorable, or attractive auditory quality.
-
B.
hasDistinctiveShape
Indicates that an entity possesses a shape or form that is notably different from others and can be easily recognized or distinguished.
-
C.
hasCallsignCompanion
Indicates that one entity serves as a companion or associated partner to another entity’s callsign.
-
D.
callCharacteristic
chosen
Indicates a defining quality, feature, or attribute associated with a particular call or calling event.
-
E.
hasCall
Indicates that one entity initiates or participates in a telephone or voice communication with another 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_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49c0d219481909830fc269fc6beb5 |
completed | April 19, 2026, 9:10 a.m. |
| PD | Predicate disambiguation | batch_69e3d8e6d2e88190ad9ef9f8a99f13e6 |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:18 a.m.