Triple
T22173894
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erotes |
E547991
|
entity |
| Predicate | haveMember |
P7638
|
FINISHED |
| Object | Hymenaeus |
—
|
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: Hymenaeus | Statement: [Erotes, haveMember, Hymenaeus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hymenaeus Context triple: [Erotes, haveMember, Hymenaeus]
-
A.
Hymenaeus
chosen
Hymenaeus is a minor Greek god associated with marriage ceremonies, often invoked in wedding songs and processions.
-
B.
Onesiphorus
Onesiphorus is a Christian figure in the New Testament known for loyally supporting and refreshing the Apostle Paul during his imprisonment.
-
C.
Sosthenes
Sosthenes is a Christian figure from the New Testament, known as a companion of the Apostle Paul and co-sender of the First Epistle to the Corinthians.
-
D.
Hermogenes
Hermogenes is a character in Plato’s dialogue "Cratylus," where he participates in a philosophical discussion with Socrates about the correctness and nature of names.
-
E.
Hermogenes
Hermogenes was a Patriarch of Moscow and All Russia, a leading figure of the Russian Orthodox Church during the early 17th century.
- 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_69e11e3d53f88190a2b690e3f25bb062 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12a6a9370819098ad65fede676c2b |
completed | April 28, 2026, 9:45 p.m. |
Created at: April 16, 2026, 8:34 p.m.