Triple
T34486054
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Goemai people |
E885325
|
entity |
| Predicate | secondaryLivelihood |
P26091
|
FINISHED |
| Object | animal husbandry |
—
|
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: animal husbandry | Statement: [Goemai people, secondaryLivelihood, animal husbandry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondaryLivelihood Context triple: [Goemai people, secondaryLivelihood, animal husbandry]
-
A.
livelihood
Indicates that one entity serves as the primary means of support, income, or subsistence for another entity.
-
B.
secondaryLandUse
Indicates a secondary or additional way in which a piece of land is used, beyond its primary designated use.
-
C.
livelihoodArea
Indicates the area or domain in which an entity earns its living or sustains its means of support.
-
D.
secondaryFood
Indicates that one entity serves as a secondary or supplementary food source in relation to another entity.
-
E.
secondaryActivity
chosen
Indicates that an entity engages in an additional, non-primary activity or role alongside its main activity.
- 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_69f349c947fc81909d30b53c194d6ea1 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ff17be6ad48190963206f2619b1b28 |
completed | May 9, 2026, 11:17 a.m. |
| PD | Predicate disambiguation | batch_69ff1724ba24819092c928fcbcb286ec |
completed | May 9, 2026, 11:14 a.m. |
Created at: May 1, 2026, 2:01 a.m.