Triple
T23257019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sande society |
E581900
|
entity |
| Predicate | maskWearers |
P134904
|
FINISHED |
| Object | female masqueraders |
—
|
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: female masqueraders | Statement: [Sande society, maskWearers, female masqueraders]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maskWearers Context triple: [Sande society, maskWearers, female masqueraders]
-
A.
hasBlackFacialMask
Indicates that an entity possesses a black-colored marking or pattern resembling a mask on its face.
-
B.
participantsWear
chosen
Indicates that the participants in an event or activity are wearing a specified item or type of clothing.
-
C.
wearerMust
Indicates that a specified item or object is required to be worn by a particular entity under certain conditions or rules.
-
D.
mask
Indicates that one entity covers, conceals, or obscures another entity, typically to hide its identity, appearance, or specific features.
-
E.
audienceWears
Indicates that members of an audience are wearing or have on a particular item or type of clothing or accessory.
- 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_69e246079f58819085eaa9c260906880 |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f194c5f5bc8190ac8776f7f7430209 |
completed | April 29, 2026, 5:19 a.m. |
| PD | Predicate disambiguation | batch_69effce4d704819092826931d430e8c4 |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:11 p.m.