Triple
T23168048
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jieng |
E578764
|
entity |
| Predicate | livelihoodFeature |
P29524
|
FINISHED |
| Object | cattle herding is central to culture |
—
|
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: cattle herding is central to culture | Statement: [Jieng, livelihoodFeature, cattle herding is central to culture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: livelihoodFeature Context triple: [Jieng, livelihoodFeature, cattle herding is central to culture]
-
A.
livelihood
chosen
Indicates that one entity serves as the primary means of support, income, or subsistence for another entity.
-
B.
livelihoodChange
Indicates a change in a person’s or group’s means of making a living, such as improvements, declines, or shifts in income-generating activities.
-
C.
livelihoodVulnerability
Indicates the degree to which an entity’s means of making a living are exposed or susceptible to harm, disruption, or loss.
-
D.
shareAgriculturalFeature
Indicates that two or more entities possess the same agricultural characteristic, condition, or resource.
-
E.
lifestyleFeature
Indicates that one entity offers, includes, or is characterized by a particular lifestyle-related amenity, attribute, or quality for 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_69e245fc75348190a0288401044c8af8 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18f2d51288190af0d5747090d8e5d |
completed | April 29, 2026, 4:55 a.m. |
| PD | Predicate disambiguation | batch_69ef89ff76808190808ee4ad9dea776b |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:03 p.m.