Triple
T27046996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atashgah |
E684664
|
entity |
| Predicate | closedAsTemple |
P32545
|
FINISHED |
| Object | late 19th century |
—
|
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: late 19th century | Statement: [Atashgah, closedAsTemple, late 19th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: closedAsTemple Context triple: [Atashgah, closedAsTemple, late 19th century]
-
A.
templeClosing
chosen
Indicates that a temple ceases or is scheduled to cease its operations or public access, marking its closure.
-
B.
lastMajorTempleClosed
Indicates the time or event at which the final significant temple associated with an entity was permanently closed.
-
C.
originalCathedralClosed
Indicates that the original cathedral has ceased operating or is no longer open to the public or for services.
-
D.
isActiveTemple
Indicates that a temple is currently functioning and in regular religious use, rather than being abandoned, ruined, or inactive.
-
E.
endsAtTemple
Indicates that an event, path, or process concludes at a temple as its final location or destination.
- 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_69ef148193c48190bb1a0cfae6a407c4 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f66c5c13808190887180099745673b |
completed | May 2, 2026, 9:27 p.m. |
| PD | Predicate disambiguation | batch_69f66abddc448190a488852f8abdeb2c |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 27, 2026, 8:11 a.m.