Triple
T36710988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sanctuary (Heichal) |
E906793
|
entity |
| Predicate | isLocatedInReligion |
P56479
|
FINISHED |
| Object | Judaism |
—
|
NE NERFINISHED |
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: Judaism | Statement: [Sanctuary (Heichal), isLocatedInReligion, Judaism]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isLocatedInReligion Context triple: [Sanctuary (Heichal), isLocatedInReligion, Judaism]
-
A.
isMajorReligionIn
Indicates that a religion is one of the primary or most widely practiced religions within a specified region or country.
-
B.
isCentralToReligion
Indicates that something plays a core, defining, or foundational role within a particular religion or religious tradition.
-
C.
isUsedByReligion
chosen
Indicates that something (such as an object, practice, text, or symbol) is employed or utilized within the context of a particular religion.
-
D.
positionInReligion
Indicates the specific role, rank, or office an entity holds within a religious organization or tradition.
-
E.
appearsInReligion
Indicates that one entity is featured, referenced, or plays a role within the religious context, texts, or traditions associated with another entity.
- 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_69f76e73ad108190a5241585f2303e9a |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fd05ba6b2c81909c62b46237d10365 |
completed | May 7, 2026, 9:35 p.m. |
| PD | Predicate disambiguation | batch_69fd03039e48819082b6e12c5453885a |
completed | May 7, 2026, 9:24 p.m. |
Created at: May 3, 2026, 4:12 p.m.