Triple
T4956398
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Polynices |
E111290
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Argia |
E170951
|
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: Argia | Statement: [Polynices, spouse, Argia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Argia Context triple: [Polynices, spouse, Argia]
-
A.
Argia
chosen
Argia is a figure in Greek mythology, a daughter of King Adrastus of Argos and the wife of Polynices, known for her role in the saga of the Seven Against Thebes.
-
B.
Aegiale
Aegiale is a figure from Greek mythology, known as one of the Heliades, the daughters of the sun god Helios.
-
C.
Caesonia
Caesonia is a Roman cognomen (family name) used by women of the gens Atia in ancient Rome.
-
D.
Agelaia
Agelaia is a genus of social wasps in the subfamily Polistinae, known for forming large, often aggressive colonies in the Neotropical region.
-
E.
Adagia
Adagia is a renowned collection of Greek and Latin proverbs compiled and annotated by the Renaissance humanist Desiderius Erasmus.
- 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_69bd4418390c8190b7e9766a2512ce55 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd71d6ba9c8190932f8d81240c3f56 |
completed | March 20, 2026, 4:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be81de17748190a26abda7d3703b8e |
completed | March 21, 2026, 11:32 a.m. |
Created at: March 20, 2026, 1:32 p.m.