Triple
T19020387
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arisbe |
E465466
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Aesopus |
E613570
|
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: Aesopus | Statement: [Arisbe, sibling, Aesopus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aesopus Context triple: [Arisbe, sibling, Aesopus]
-
A.
Aesopus
chosen
Aesopus is a figure from Greek mythology, known as a river god associated with one of the many rivers personified in ancient Greek religion.
-
B.
Aesop's fables
Aesop's fables are a classic collection of short moral stories, traditionally attributed to the ancient Greek storyteller Aesop, that use animals and everyday situations to illustrate ethical lessons.
-
C.
Aesacus
Aesacus is a minor figure in Greek mythology, a son of King Priam of Troy known for his tragic love story and transformation into a seabird.
-
D.
Jean de La Fontaine
Jean de La Fontaine was a 17th-century French poet and fabulist best known for his enduring collection of moral fables inspired by Aesop.
-
E.
Peter the goatherd
Peter the goatherd is a young Swiss boy who tends goats in the Alps and serves as Heidi’s close friend and companion in Johanna Spyri’s classic novel.
- 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_69d8dd025c188190a1d81f5b4ec7e2c6 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6de93408190a98dea2319f1af62 |
completed | April 20, 2026, 7:33 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a05be5244dc819087e2269c02c6f4c7 |
completed | May 14, 2026, 12:21 p.m. |
Created at: April 10, 2026, 12:02 p.m.