Triple
T4257225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Telesterion at Eleusis |
E96004
|
entity |
| Predicate | AnaktoronUsedFor |
P54993
|
FINISHED |
| Object | keeping sacred objects of the Mysteries |
—
|
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: keeping sacred objects of the Mysteries | Statement: [Telesterion at Eleusis, AnaktoronUsedFor, keeping sacred objects of the Mysteries]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: AnaktoronUsedFor Context triple: [Telesterion at Eleusis, AnaktoronUsedFor, keeping sacred objects of the Mysteries]
-
A.
notTypicallyUsedFor
Indicates that something is generally not used for a particular purpose, function, or activity under normal circumstances.
-
B.
usedAsAnalogFor
Indicates that one entity is employed as a comparison or illustrative counterpart to help explain, represent, or understand another entity.
-
C.
hasAltar
Indicates that one entity possesses, contains, or includes an altar as part of its features or components.
-
D.
antlerType
Indicates the specific kind or classification of antlers that an entity possesses or is associated with.
-
E.
hasTorii
Indicates that something possesses or features a torii gate as part of its structure or environment.
- F. None of above. chosen
Provenance (4 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_69b3454095ac81909c2494f7ff294af1 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34ec321008190b2cc1aca6ab690c4 |
completed | March 12, 2026, 11:39 p.m. |
| PD | Predicate disambiguation | batch_69b347f73e008190a908a48ef389945a |
completed | March 12, 2026, 11:10 p.m. |
| PDg | Predicate description generation | batch_69b34e04ef1c81908bb34ae1cbfab1e6 |
completed | March 12, 2026, 11:36 p.m. |
Created at: March 12, 2026, 11:06 p.m.