Triple
T20480718
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Persée et Andromède |
E502443
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object | Persée |
—
|
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: Persée | Statement: [Persée et Andromède, featuresCharacter, Persée]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Persée Context triple: [Persée et Andromède, featuresCharacter, Persée]
-
A.
Hippolyte
Hippolyte is a tragic hero from Greek mythology, known as the chaste son of Theseus whose doomed love and fatal misfortunes have inspired numerous literary and operatic works.
-
B.
Hippolyte
Hippolyte is the given name of Hippolyte Fizeau, a 19th-century French physicist known for pioneering measurements of the speed of light.
-
C.
Perseus
chosen
Perseus is a legendary Greek hero famed for slaying the Gorgon Medusa and rescuing Andromeda.
-
D.
Paride
Paride is the Italian name for Paris, the Trojan prince in Greek mythology whose abduction of Helen helped spark the Trojan War.
-
E.
Telophorus
Telophorus is a genus of bushshrikes, medium-sized insectivorous passerine birds native to sub-Saharan Africa.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4af32848190aea80682b44d5d6e |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69b56dd248190b6bc4e513aff3c9c |
completed | April 20, 2026, 9:32 p.m. |
Created at: April 16, 2026, 11:34 a.m.