Triple
T29058561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | sanctuary of Hera Akraia |
E735460
|
entity |
| Predicate | hasCultAspectOfDeity |
P73550
|
FINISHED |
| Object | Hera Akraia |
—
|
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: Hera Akraia | Statement: [sanctuary of Hera Akraia, hasCultAspectOfDeity, Hera Akraia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCultAspectOfDeity Context triple: [sanctuary of Hera Akraia, hasCultAspectOfDeity, Hera Akraia]
-
A.
hasDeityAspect
chosen
Indicates that one entity embodies, represents, or functions as a specific divine aspect or manifestation of another deity.
-
B.
hasCultEpithetOfDeity
Indicates that a specific cult epithet or title is associated with, or used for, a particular deity.
-
C.
hasDeity
Indicates that one entity recognizes, worships, or is associated with another entity as its deity or divine figure.
-
D.
hasComponentDeity
Indicates that an entity (such as a religion, mythology, or pantheon) includes a particular deity as one of its constituent or associated divine figures.
-
E.
hasCultOrLegend
Indicates that an entity is associated with, or is the subject of, a cult, myth, or legendary tradition.
- 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_69f077e85498819088b65186550da8cd |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f7be53890081909b1d93f30a8f31c6 |
completed | May 3, 2026, 9:29 p.m. |
| PD | Predicate disambiguation | batch_69f7bccacbac8190978976324c67db28 |
completed | May 3, 2026, 9:23 p.m. |
Created at: April 28, 2026, 10:13 a.m.