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.