Triple
T24121048
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tani peoples |
E597652
|
entity |
| Predicate | sharesMythOfAncestor |
P111775
|
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, sharesMythOfAncestor, Abotani]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesMythOfAncestor Context triple: [Tani peoples, sharesMythOfAncestor, Abotani]
-
A.
sharesMythosWith
chosen
Indicates that two entities are associated with, or originate from, the same mythological tradition, narrative system, or shared set of myths.
-
B.
mythologicalFamily
Indicates a familial relationship between entities within a mythological or legendary context.
-
C.
hasMythologicalFamily
Indicates that an entity is related to another entity as part of its mythological family or lineage (e.g., gods, heroes, or legendary ancestors).
-
D.
mythicalAncestorMother
Indicates that one entity is regarded as the mythological or legendary mother-ancestor of another entity.
-
E.
mythologicalContent
Indicates that the subject contains, references, or is associated with myths, mythological narratives, or myth-based elements.
- 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.