Triple
T25558202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mende people |
E640631
|
entity |
| Predicate | genderRoleInstitution |
P69451
|
FINISHED |
| Object | Sande society |
—
|
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: Sande society | Statement: [Mende people, genderRoleInstitution, Sande society]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: genderRoleInstitution Context triple: [Mende people, genderRoleInstitution, Sande society]
-
A.
sexualRole
Indicates the specific sexual function, position, or behavioral role one entity assumes in a sexual interaction or relationship with another.
-
B.
genderRoleAssociation
Indicates an association between a gender and a particular social role, behavior, or expectation.
-
C.
genderRoleSignificance
Indicates the extent to which gender roles are considered important, influential, or defining within a given relationship, context, or interaction.
-
D.
genderNorms
Indicates socially constructed expectations or rules about how individuals should behave, appear, or identify based on their perceived gender.
-
E.
hasGenderRole
chosen
Indicates that an entity is associated with, or expected to perform, a particular socially defined gender-based role or set of behaviors.
- 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_69e75dc1beb08190bac7d76b8d6e7bc4 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f8cbeda88190a356da7f7ae3437d |
completed | May 2, 2026, 1:14 p.m. |
| PD | Predicate disambiguation | batch_69f49377411c8190b2188de444d76795 |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 21, 2026, 3:44 p.m.