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.