Triple
T24685289
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chopi people |
E611266
|
entity |
| Predicate | poetryFunction |
P156976
|
FINISHED |
| Object | historical narration |
—
|
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: historical narration | Statement: [Chopi people, poetryFunction, historical narration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: poetryFunction Context triple: [Chopi people, poetryFunction, historical narration]
-
A.
poetryFunction
chosen
Indicates that one entity serves a particular role, purpose, or function within the domain of poetry for another entity.
-
B.
poem
Indicates that one entity is a poem created, authored, or associated with another entity.
-
C.
usesPoeticProgram
Indicates that one entity employs or applies a poetic program—such as a structured, rule-based, or stylistically poetic system—in relation to another entity or context.
-
D.
poeticStyle
Indicates the stylistic or formal manner in which something is expressed in poetry, such as its structure, tone, and linguistic features.
-
E.
wrotePoemAbout
Indicates that one entity is the author of a poem whose subject or theme is 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_69e2c4d678b081908910f4271627a31a |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f422aee0408190899efe7e24ef2b40 |
completed | May 1, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69f420e92cc88190a803aecdae78a051 |
completed | May 1, 2026, 3:41 a.m. |
Created at: April 18, 2026, 3:17 a.m.