Triple
T26138287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | معبد بتاح في منف |
E659441
|
entity |
| Predicate | كان مركزًا لـ |
P145012
|
FINISHED |
| Object | عبادة الإله بتاح |
—
|
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: عبادة الإله بتاح | Statement: [معبد بتاح في منف, كان مركزًا لـ, عبادة الإله بتاح]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: كان مركزًا لـ Context triple: [معبد بتاح في منف, كان مركزًا لـ, عبادة الإله بتاح]
-
A.
previouslyCenteredOn
Indicates that something was formerly the main focus, reference point, or central subject of another thing, but is no longer in that central position.
-
B.
historicalCenterFor
chosen
Indicates that one entity has served as a central or focal place of historical significance, activity, or development for another entity.
-
C.
leadershipCenterFor
Indicates that one entity serves as the primary hub or focal institution providing leadership, guidance, or coordination for another entity or domain.
-
D.
wasMilitaryHeadquartersOf
Indicates that a place or facility served as the main command center or headquarters for a specific military force or organization.
-
E.
isFormerMilitaryCenter
Indicates that a place previously served as a military center or base but no longer holds that function.
- 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_69ee5bc3c20c8190bf2cf272f4170e95 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f60be1d2408190820365bf7d8436bd |
completed | May 2, 2026, 2:36 p.m. |
| PD | Predicate disambiguation | batch_69f5b0021da88190bdd4cf2698c23edf |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 26, 2026, 8:18 p.m.