Triple
T20082892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barbary macaque |
E500046
|
entity |
| Predicate | genus |
P87
|
FINISHED |
| Object | Macaca |
—
|
NE NERFINISHED |
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: Macaca | Statement: [Barbary macaque, genus, Macaca]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Macaca Context triple: [Barbary macaque, genus, Macaca]
-
A.
Macaca
chosen
Macaca is a diverse genus of Old World monkeys that includes numerous macaque species widely distributed across Asia and parts of North Africa.
-
B.
Love Monkey
Love Monkey is a short-lived 2006 American television dramedy series about a music executive navigating his personal and professional life in New York City.
-
C.
Monkey
Monkey is a swift, acrobatic kung fu master and member of the Furious Five in the Kung Fu Panda franchise, known for his playful personality and agility in combat.
-
D.
Monkey
"Monkey" is a song by the British rock band Bush from their 1994 debut album *Sixteen Stone*.
-
E.
Monkey
Monkey is the superhero chimpanzee sidekick of Dexter in the animated series Dexter’s Laboratory, starring in the show’s recurring segment “Dial M for Monkey.”
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da627770948190997f486f9a2e370f |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6655946f48190a6b4cb13ea4e212a |
completed | April 20, 2026, 5:41 p.m. |
Created at: April 11, 2026, 3:41 p.m.