Triple
T26351028
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Himba |
E662900
|
entity |
| Predicate | ritualObjectRole |
P7123
|
FINISHED |
| Object | ancestral fire |
—
|
LITERAL FINISHED |
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: ancestral fire | Statement: [Himba, ritualObjectRole, ancestral fire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ritualObjectRole Context triple: [Himba, ritualObjectRole, ancestral fire]
-
A.
roleInRitual
Indicates the specific function, position, or responsibility an entity holds within a particular ritual or ceremonial activity.
-
B.
hasRitualObject
chosen
Indicates that an entity possesses, uses, or is associated with an object specifically employed in a ritual or ceremonial context.
-
C.
hasRitualRoleIn
Indicates that an entity serves a specific ritual function or role within a particular ritual, ceremony, or sacred practice.
-
D.
ritualsDirectedAt
Indicates that certain rituals are performed with a specific entity, object, or target as their intended focus or recipient.
-
E.
hasRitualObjectMaterial
Indicates that a ritual object is made from, composed of, or primarily constructed using a specified material.
- 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_69ee8130fc44819094e5ab1da201cd7b |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f60feb75a08190be5002cfacabce78 |
completed | May 2, 2026, 2:53 p.m. |
| PD | Predicate disambiguation | batch_69f602d2ec748190ae95154f34c7878f |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 26, 2026, 10:45 p.m.