Triple
T4886221
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amphitryon |
E109444
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Sthenelus |
E148402
|
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: Sthenelus | Statement: [Amphitryon, relative, Sthenelus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sthenelus Context triple: [Amphitryon, relative, Sthenelus]
-
A.
Sthenelus
chosen
Sthenelus is a figure in Greek mythology, known as a king of Mycenae and a descendant of the hero Perseus.
-
B.
Palamedes
Palamedes is a 1625 Dutch tragedy by Joost van den Vondel that allegorically critiques political and religious injustice in the Dutch Republic.
-
C.
Alcathous
Alcathous is the ancient acropolis of the Greek city of Megara, serving as its fortified citadel and religious center.
-
D.
Heleus
Heleus is a figure in Greek mythology known as a son of Perseus and Andromeda.
-
E.
Terpsion
Terpsion is a character in Plato’s dialogues, notably appearing in the Theaetetus as one of the interlocutors involved in recounting Socratic conversations.
- 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_69bd440f71348190b99938e59fb7f9a1 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6e01872c81909607010c10538ad1 |
completed | March 20, 2026, 3:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be77975ad08190a427bcf1c01e364f |
completed | March 21, 2026, 10:48 a.m. |
Created at: March 20, 2026, 1:28 p.m.