Triple
T896511
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hades |
E19357
|
entity |
| Predicate | depictedWith |
P1581
|
FINISHED |
| Object | Cerberus |
E105612
|
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: Cerberus | Statement: [Hades, depictedWith, Cerberus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cerberus Context triple: [Hades, depictedWith, Cerberus]
-
A.
Cerberus
chosen
Cerberus is the multi-headed hound from Greek mythology that guards the entrance to the underworld, preventing the dead from leaving.
-
B.
Cacus
Cacus is a fire-breathing giant and notorious cattle-stealing monster from Roman mythology, best known for being slain by the hero Hercules.
-
C.
Lycus
Lycus is a figure in Greek mythology, traditionally known as a son of the Pleiad Celaeno and the god Poseidon.
-
D.
Argus
Argus is an early distributed programming language known for pioneering concepts in fault-tolerant, distributed systems and influencing modern object-oriented and concurrent programming.
-
E.
Antaeus
Antaeus is a giant in Greek mythology, famed for drawing his strength from contact with the earth and being defeated by Heracles.
- 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_69a4939d37188190848be3d426ebc9ae |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b2b9339081909af5ab231be39bb0 |
completed | March 1, 2026, 9:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a7c730693c81909dfda6c5aca876c5 |
completed | March 4, 2026, 5:46 a.m. |
Created at: March 1, 2026, 7:39 p.m.