Triple
T14381925
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Temple of Apollo at Delphi |
E356622
|
entity |
| Predicate | earlierTempleDestroyedBy |
P92871
|
FINISHED |
| Object | fire |
—
|
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: fire | Statement: [Temple of Apollo at Delphi, earlierTempleDestroyedBy, fire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: earlierTempleDestroyedBy Context triple: [Temple of Apollo at Delphi, earlierTempleDestroyedBy, fire]
-
A.
firstPalaceDestroyedBy
Indicates that the subject’s first palace was destroyed by the specified agent or cause.
-
B.
shrineDestroyedBy
chosen
Indicates that a shrine has been ruined, demolished, or otherwise destroyed as a result of the actions of a specified agent or cause.
-
C.
statusAfterTempleDestruction
Indicates the condition or state of an entity that applies specifically after the destruction of the temple.
-
D.
firstPalaceDestroyedIn
Indicates that the first palace associated with an entity was destroyed in a specified event, time, or place.
-
E.
secondPalaceDestroyedBy
Indicates that the second palace associated with an entity was destroyed by another specified agent or cause.
- 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_69d8279163a081908aec45c0e3f1e02f |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de900bbfb08190a1e56f281a2374c0 |
completed | April 14, 2026, 7:05 p.m. |
| PD | Predicate disambiguation | batch_69de2a9cb3e081909f6b33fdd939bb9e |
completed | April 14, 2026, 11:53 a.m. |
Created at: April 10, 2026, 1:16 a.m.