Triple
T2514373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erytheia |
E52776
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Aegle |
E51870
|
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: Aegle | Statement: [Erytheia, sibling, Aegle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aegle Context triple: [Erytheia, sibling, Aegle]
-
A.
Aegle
chosen
Aegle is a figure from Greek mythology, often identified as one of the Hesperides, the nymphs associated with a blissful garden at the western edge of the world.
-
B.
Scidrus
Scidrus was an ancient Greek colonial settlement in southern Italy associated with the wealthy city of Sybaris.
-
C.
Macleaya
Macleaya is a small genus of tall, herbaceous flowering plants known as plume poppies, cultivated for their ornamental foliage and feathery flower plumes.
-
D.
Phasaelis
Phasaelis was a Nabatean princess, daughter of King Aretas IV, best known as the first wife of Herod Antipas whose repudiation of her led to political and military conflict.
-
E.
Ennepetal
Ennepetal is a town in North Rhine-Westphalia, Germany, known for its industrial heritage and scenic location in the Ennepe-Ruhr district.
- 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_69ab4958e76481908a235377dd921c9e |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abd20c8ab0819096d6a654039beb39 |
completed | March 7, 2026, 7:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af2b934d3c81909627a5f4d6e6ca6a |
completed | March 9, 2026, 8:20 p.m. |
Created at: March 6, 2026, 9:46 p.m.