Triple
T31743501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sari, Papua New Guinea |
E810201
|
entity |
| Predicate | livelihoodPattern |
P162656
|
FINISHED |
| Object | household-based farming |
—
|
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: household-based farming | Statement: [Sari, Papua New Guinea, livelihoodPattern, household-based farming]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: livelihoodPattern Context triple: [Sari, Papua New Guinea, livelihoodPattern, household-based farming]
-
A.
livelihood
Indicates that one entity serves as the primary means of support, income, or subsistence for another entity.
-
B.
livelihoodArea
chosen
Indicates the area or domain in which an entity earns its living or sustains its means of support.
-
C.
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.
-
D.
livelihoodChallenges
Indicates difficulties or obstacles that negatively affect an entity’s ability to secure or maintain its means of living or income.
-
E.
livelihoodVulnerability
Indicates the degree to which an entity’s means of making a living are exposed or susceptible to harm, disruption, or loss.
- 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_69f348e233cc819083b6695f70cd75d8 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6ab4c16e08190ae522564534d243d |
completed | May 3, 2026, 1:56 a.m. |
| PD | Predicate disambiguation | batch_69f6aa20a1588190a53533fc9764efb2 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 30, 2026, 11:25 p.m.