Triple
T5363006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aeëtes |
E103064
|
entity |
| Predicate | mother |
P120
|
FINISHED |
| Object | Perseis |
E419255
|
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: Perseis | Statement: [Aeëtes, mother, Perseis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Perseis Context triple: [Aeëtes, mother, Perseis]
-
A.
Phigaleia
Phigaleia is an ancient town in southwestern Arcadia, Greece, known for its historical significance and nearby classical ruins.
-
B.
Terpsion
Terpsion is a character in Plato’s dialogues, notably appearing in the Theaetetus as one of the interlocutors involved in recounting Socratic conversations.
-
C.
Peraea
Peraea is a historical region east of the Jordan River that formed part of ancient Judea during the Second Temple period.
-
D.
Adrasteia
chosen
Adrasteia is a nymph in Greek mythology associated with nurturing the infant Zeus and sometimes linked with divine retribution and inevitability.
-
E.
Partheni
Partheni is a small coastal village and settlement on the Greek island of Leros in the Dodecanese.
- 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_69bd43daa3e4819090b59d127db70e57 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd865b9b808190a1e8c283ba28d645 |
completed | March 20, 2026, 5:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf21f2bc708190b596c5402fa07e75 |
completed | March 21, 2026, 10:55 p.m. |
Created at: March 20, 2026, 2:02 p.m.