Triple
T36930927
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hazo |
E913477
|
entity |
| Predicate | appearsInTextualSection |
P179350
|
FINISHED |
| Object | Patriarchal narratives |
—
|
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: Patriarchal narratives | Statement: [Hazo, appearsInTextualSection, Patriarchal narratives]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appearsInTextualSection Context triple: [Hazo, appearsInTextualSection, Patriarchal narratives]
-
A.
canonicalTextSection
Indicates that one text section is the authoritative or standard version associated with another representation or variant of that section.
-
B.
coveredSectionsLocation
Indicates the specific location or area where the covered sections are situated or applied.
-
C.
usesSectionOf
Indicates that one entity makes use of a specific section or part of another entity.
-
D.
chapterAppearance
chosen
Indicates that an entity appears or is present in a specific chapter of a work.
-
E.
coveredSection
Indicates that one section is physically or conceptually overlaid, protected, or enclosed by another, such that it is considered to be under that section’s coverage.
- 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_69f76e896c988190880c130e01303dd4 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fe9b0276d48190b554fa22b043e6d8 |
completed | May 9, 2026, 2:25 a.m. |
| PD | Predicate disambiguation | batch_69fe999692b081909921e1148d66f0ef |
completed | May 9, 2026, 2:19 a.m. |
Created at: May 3, 2026, 4:13 p.m.