Triple
T1705872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atreid dynasty |
E36870
|
entity |
| Predicate | hasProgenitor |
P369
|
FINISHED |
| Object | Atreus |
E192272
|
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: Atreus | Statement: [Atreid dynasty, hasProgenitor, Atreus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Atreus Context triple: [Atreid dynasty, hasProgenitor, Atreus]
-
A.
Atreus
chosen
Atreus is a legendary king in Greek mythology, father of Agamemnon and Menelaus and a central figure in the tragic saga of the House of Atreus.
-
B.
Astakos
Astakos is a coastal town in western Greece known as a regional port and ferry hub on the Ionian Sea.
-
C.
Sthenelus
Sthenelus is a figure in Greek mythology, known as a king of Mycenae and a descendant of the hero Perseus.
-
D.
Polydectes
Polydectes is a king in Greek mythology best known for sending Perseus on the quest to slay Medusa in an attempt to get rid of him.
-
E.
Telegonus
Telegonus is a figure in Greek mythology, known as the son of the sorceress Circe and the hero Odysseus, who unwittingly killed his father and later married Penelope.
- 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_69a88617439c819094ffb5d16a0f6307 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abaffc4e5c81908ce0b9cfe833445e |
completed | March 7, 2026, 4:56 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ada97a55948190b4c58503d53132f0 |
completed | March 8, 2026, 4:53 p.m. |
Created at: March 4, 2026, 7:30 p.m.