Triple
T4756992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cerberus |
E105612
|
entity |
| Predicate | hasSibling |
P363
|
FINISHED |
| Object | Nemean Lion |
E377343
|
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: Nemean Lion | Statement: [Cerberus, hasSibling, Nemean Lion]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nemean Lion Context triple: [Cerberus, hasSibling, Nemean Lion]
-
A.
Nemean Lion
chosen
The Nemean Lion is a fearsome, invulnerable lion from Greek mythology best known as the monstrous beast slain by Heracles in the first of his Twelve Labors.
-
B.
Erymanthian Boar
The Erymanthian Boar is a fearsome mythical creature from Greek mythology, a gigantic wild boar that Heracles was tasked with capturing alive as one of his Twelve Labors.
-
C.
Cretan Bull
The Cretan Bull is a fearsome mythical bull from Greek mythology that Heracles was tasked with capturing as one of his Twelve Labours.
-
D.
Ladon
Ladon is the many-headed dragon of Greek mythology who watches over the golden apples in the Garden of the Hesperides.
-
E.
Ceryneian Hind
The Ceryneian Hind is a mythical, swift, golden-horned deer sacred to Artemis that Heracles was tasked with capturing alive as one of his Twelve Labours.
- 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_69bd43f14cac819081c7c69803648211 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd64ec16a0819089836e4388b555f6 |
completed | March 20, 2026, 3:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be3a72ba908190ad9b423aea2a22b8 |
completed | March 21, 2026, 6:28 a.m. |
Created at: March 20, 2026, 1:20 p.m.