Triple

T24121049
Position Surface form Disambiguated ID Type / Status
Subject Tani peoples E597652 entity
Predicate commonAncestralFigure P8000 FINISHED
Object Abotani NE NERFINISHED

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: Abotani | Statement: [Tani peoples, commonAncestralFigure, Abotani]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: commonAncestralFigure
Context triple: [Tani peoples, commonAncestralFigure, Abotani]
  • A. sharesCommonAncestorWith
    Indicates that two entities have at least one ancestor in common in their lineage or hierarchy.
  • B. ancestralLinks
    Indicates a genealogical relationship where one entity is an ancestor of, or connected through a line of descent to, another entity.
  • C. foundingAncestor chosen
    Indicates that one entity is the original progenitor or earliest known ancestor from whom another entity or lineage descends.
  • D. ancestor
    Indicates that one entity is a forebear of another in a lineage, occurring in an earlier generation and connected through one or more parent-child relationships.
  • E. allegedAncestor
    Indicates that one entity is claimed or suspected to be an ancestor of another, without confirming that the ancestral relationship is true.
  • 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_69e288c74200819098ab875b592cb39f completed April 17, 2026, 7:23 p.m.
NER Named-entity recognition batch_69f1dee2defc81909df55900769fef5b completed April 29, 2026, 10:35 a.m.
PD Predicate disambiguation batch_69f1765650fc8190a6bc1eb512b240bf completed April 29, 2026, 3:09 a.m.
Created at: April 17, 2026, 11:05 p.m.