Triple
T2106311
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quba Mosque |
E42401
|
entity |
| Predicate | genderSegregation |
P25470
|
FINISHED |
| Object | separate prayer areas for men and women |
—
|
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: separate prayer areas for men and women | Statement: [Quba Mosque, genderSegregation, separate prayer areas for men and women]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: genderSegregation Context triple: [Quba Mosque, genderSegregation, separate prayer areas for men and women]
-
A.
genderDivision
chosen
Indicates a relationship where roles, responsibilities, or categories are separated or distinguished based on gender.
-
B.
sexOrGender
Indicates that one entity has a specified biological sex or socially constructed gender identity.
-
C.
genderEquality
Indicates that the relationship or action promotes, reflects, or ensures equal rights, opportunities, and treatment for all genders without discrimination.
-
D.
genderCategories
Indicates the classification of an entity into one or more gender-related categories or identities.
-
E.
isSingleSex
Indicates that the entity involves or is restricted to only one biological sex or gender, rather than being mixed or coeducational.
- 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_69a8871040f08190aac2e2d0ab6b47ad |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abbaddeb148190b728bce7a7b041fb |
completed | March 7, 2026, 5:42 a.m. |
| PD | Predicate disambiguation | batch_69abb7b7b6288190afa11b4d93bd5666 |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:43 p.m.