Triple
T9702524
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cretheus |
E234811
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Salmoneus |
E454470
|
NE 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: Salmoneus | Statement: [Cretheus, sibling, Salmoneus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Salmoneus Context triple: [Cretheus, sibling, Salmoneus]
-
A.
Salmoneus
chosen
Salmoneus is a figure in Greek mythology, a king of Elis known for his hubristic attempt to imitate Zeus and for being the father of Tyro.
-
B.
Cretheus
Cretheus is a figure in Greek mythology, a king of Iolcus and ancestor of the hero Jason.
-
C.
Pheneus
Pheneus was an ancient Arcadian city in the northeastern Peloponnese, known from Greek mythology and classical geography.
-
D.
Dagisthaeus
Dagisthaeus was a 6th-century Byzantine general known for leading imperial forces during the Lazic War against the Sasanian Empire.
-
E.
Eurytion
Eurytion is a herdsman in Greek mythology best known for guarding the cattle of the three-bodied giant Geryon, whom Heracles killed during his tenth labor.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca84cc78808190a56f3402b7c139a7 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9d7283188190bd50e18f643ad0d3 |
completed | April 1, 2026, 10:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1bcc0117c8190bc82a985ce59623d |
completed | April 5, 2026, 1:37 a.m. |
Created at: March 30, 2026, 8:18 p.m.