Triple
T2936774
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pythia |
E79286
|
entity |
| Predicate | consultationFrequency |
P2557
|
FINISHED |
| Object | originally once a year on the birthday of Apollo |
—
|
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: originally once a year on the birthday of Apollo | Statement: [Pythia, consultationFrequency, originally once a year on the birthday of Apollo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: consultationFrequency Context triple: [Pythia, consultationFrequency, originally once a year on the birthday of Apollo]
-
A.
meetingFrequency
chosen
Indicates how often a meeting or recurring gathering takes place over a given period.
-
B.
consultationMethod
Indicates the way or medium through which a consultation is conducted or delivered.
-
C.
hasCommunicationFrequency
Indicates how often communication occurs between the related entities.
-
D.
consultsOn
Indicates that one entity provides expert advice, guidance, or professional input to another entity regarding a specific subject, project, or decision.
-
E.
consulted
Indicates that one entity sought advice, information, or guidance from another entity.
- 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_69ad8b0fbab081908f6a61567c045d8d |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad983f91c48190b409d8f522cab08b |
completed | March 8, 2026, 3:39 p.m. |
| PD | Predicate disambiguation | batch_69ad96088fb481909976b436c2b729d9 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:56 p.m.