Triple
T21059436
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Epirotes |
E518811
|
entity |
| Predicate | majorSanctuaryType |
P5445
|
FINISHED |
| Object | oracle of Zeus |
—
|
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: oracle of Zeus | Statement: [Epirotes, majorSanctuaryType, oracle of Zeus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: majorSanctuaryType Context triple: [Epirotes, majorSanctuaryType, oracle of Zeus]
-
A.
hasMajorSanctuary
chosen
Indicates that an entity possesses or is associated with a primary or principal sanctuary location.
-
B.
biosphereReserveType
Indicates the specific classification or category of a biosphere reserve within a defined typology or management framework.
-
C.
modernProtectedArea
Indicates that an area is designated and managed as a contemporary legally recognized protected area under modern conservation frameworks.
-
D.
stateProtectedAreaType
Indicates that an area is designated as a specific type or category of state-protected area.
-
E.
partOfProtectedAreaCategory
Indicates that one protected area belongs to, or is classified under, a specific protected area category.
- 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_69e0b5053ac48190921529544959e906 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fd842e8881909f4ffc4c43b7fa9f |
completed | April 21, 2026, 4:31 a.m. |
| PD | Predicate disambiguation | batch_69e5dbf9d71881908cd85dfc37db93ca |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 2:37 p.m.