Triple
T21028596
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | House of Cadmus |
E518004
|
entity |
| Predicate | hasCurseSource |
P7531
|
FINISHED |
| Object | slaying of Ares’ dragon |
—
|
LITERAL 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: slaying of Ares’ dragon | Statement: [House of Cadmus, hasCurseSource, slaying of Ares’ dragon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCurseSource Context triple: [House of Cadmus, hasCurseSource, slaying of Ares’ dragon]
-
A.
hasCursedLocation
Indicates a relationship where a location is affected by or associated with a curse.
-
B.
associatedCurse
chosen
Indicates that one entity is linked to, affected by, or bears responsibility for a particular curse related to another entity.
-
C.
curseCondition
Indicates a condition or state in which an entity is affected by a curse or cursed effect.
-
D.
attemptedCurseReversal
Indicates an action where one entity tried, but did not necessarily succeed, to reverse or undo a curse affecting another entity.
-
E.
hasMythSource
Indicates that something derives from, is based on, or is supported by a particular myth or mythological source.
- F. None of above.
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_69e0b503275c8190afd9a163f997c709 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc7efda081909a4de1c389166bf2 |
completed | April 21, 2026, 4:26 a.m. |
| PD | Predicate disambiguation | batch_69e5dbf274ac81909bbf245627dc8fdc |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 1:55 p.m.