Triple
T29514070
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harem (family and women’s quarters) |
E748741
|
entity |
| Predicate | variedAcross |
P154440
|
FINISHED |
| Object | different Middle Eastern regions |
—
|
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: different Middle Eastern regions | Statement: [Harem (family and women’s quarters), variedAcross, different Middle Eastern regions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: variedAcross Context triple: [Harem (family and women’s quarters), variedAcross, different Middle Eastern regions]
-
A.
variesOver
chosen
Indicates that the value, state, or behavior of one entity changes as a function of another entity or parameter.
-
B.
varietyOf
Indicates that one entity is a specific type, kind, or variant of another, more general entity.
-
C.
viewVariesAmong
Indicates that the way something is viewed, perceived, or interpreted differs across multiple entities or contexts.
-
D.
hasVarietyOf
Indicates that an entity possesses or offers multiple different types, forms, or versions of something.
-
E.
yieldsViaVariation
Indicates that one entity produces or results in another through a process of variation or modification.
- 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_69f0bd461c208190bec20bbf24e02cc5 |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f66c61be488190b4a8f39c94a76409 |
completed | May 2, 2026, 9:28 p.m. |
| PD | Predicate disambiguation | batch_69f6633ac8a88190ab0cda62bbfcf9b0 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 4:35 p.m.