Triple
T38434030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Banu Hanifa |
E903884
|
entity |
| Predicate | tribalNisba |
P84454
|
FINISHED |
| Object | al-Hanafi |
—
|
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: al-Hanafi | Statement: [Banu Hanifa, tribalNisba, al-Hanafi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tribalNisba Context triple: [Banu Hanifa, tribalNisba, al-Hanafi]
-
A.
usedNisba
chosen
Indicates that one entity is described or classified using a nisba (relational adjective or gentilic) derived from another entity.
-
B.
usesNisba
Indicates that one entity forms or applies a nisba (a relational or adjectival form, often derived from a name or place) to or in relation to another entity.
-
C.
tribeName
Indicates the name assigned to a tribe in the relationship.
-
D.
tribalAffiliationType
Indicates the specific type or category of tribal affiliation that characterizes the relationship between an entity and a tribe.
-
E.
tribalStatus
Indicates that an entity holds a particular affiliation, recognition, or classification with respect to a tribe or tribal community.
- 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_69f76e6a2024819081aa04f4932f89d2 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fcd313e61c8190b174b331365b803f |
completed | May 7, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f6b2e08190bf0300ae7c9ae67a |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:31 p.m.