Triple
T16756238
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Azariqa |
E407212
|
entity |
| Predicate | viewOnWomenAndChildren |
P64114
|
FINISHED |
| Object | permitted killing of opponents’ women and children |
—
|
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: permitted killing of opponents’ women and children | Statement: [Azariqa, viewOnWomenAndChildren, permitted killing of opponents’ women and children]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: viewOnWomenAndChildren Context triple: [Azariqa, viewOnWomenAndChildren, permitted killing of opponents’ women and children]
-
A.
viewOnWomen
chosen
Indicates a person's attitudes, beliefs, or perspectives regarding women and gender roles.
-
B.
viewOnGood
Indicates a positive or approving perspective held toward something.
-
C.
viewOnImages
Indicates that one entity views or displays another entity specifically in the form of images.
-
D.
womenSection
Indicates that something is designated as belonging to, located in, or associated with the women's section or area.
-
E.
viewMaryAs
Indicates that one entity perceives, regards, or interprets Mary in a particular way or role.
- 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_69d8839174188190909f190097207065 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3abe831ec8190bac05b07db6153c1 |
completed | April 18, 2026, 4:06 p.m. |
| PD | Predicate disambiguation | batch_69e319cbd79c8190a03587a61c18bec0 |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:21 a.m.