Triple
T25410854
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kinana tribe |
E636690
|
entity |
| Predicate | ancestralGroupOf |
P35417
|
FINISHED |
| Object | Banu Hashim |
—
|
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: Banu Hashim | Statement: [Kinana tribe, ancestralGroupOf, Banu Hashim]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ancestralGroupOf Context triple: [Kinana tribe, ancestralGroupOf, Banu Hashim]
-
A.
ancestralGroup
chosen
Indicates that one entity is a broader ancestral lineage, population, or group from which the other entity descends or originates.
-
B.
ancestralDomainOf
Indicates that one entity is the original or historically prior domain from which another domain is derived or descended.
-
C.
ancestralSubgroups
Indicates that one group consists of or descends from earlier, foundational subgroups within a lineage or hierarchy.
-
D.
ancestralDomain
Indicates that one entity is the traditional or long-held territory or domain from which another entity originates or to which it is ancestrally connected.
-
E.
tribeProgenitorOf
Indicates that one entity is the original ancestor or founding progenitor from which a particular tribe or tribal group descends.
- 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_69e75db361d881908d8701c856da6413 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5b00dfbf08190b20120c052126935 |
completed | May 2, 2026, 8:04 a.m. |
| PD | Predicate disambiguation | batch_69f4683b34748190818428489a226124 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 1:53 p.m.