Triple
T28651320
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andvari's ring |
E725206
|
entity |
| Predicate | typeOfCurse |
P197699
|
FINISHED |
| Object | hereditary curse |
—
|
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: hereditary curse | Statement: [Andvari's ring, typeOfCurse, hereditary curse]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfCurse Context triple: [Andvari's ring, typeOfCurse, hereditary curse]
-
A.
associatedCurse
Indicates that one entity is linked to, affected by, or bears responsibility for a particular curse related to another entity.
-
B.
placeOfCurse
Indicates the specific location where a curse is cast, placed, or takes effect on an entity.
-
C.
curseCondition
Indicates a condition or state in which an entity is affected by a curse or cursed effect.
-
D.
timeOfCurse
Indicates the specific time at which a curse is cast, activated, or takes effect in relation to an entity or event.
-
E.
curseName
Indicates that one entity assigns, uses, or is associated with a specific name or label used as a curse toward another entity.
- F. None of above. chosen
Provenance (4 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_69f01d8423888190bd2f4e52605bf261 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69fea2d0a4d08190aa06aeb902a02d5a |
completed | May 9, 2026, 2:58 a.m. |
| PD | Predicate disambiguation | batch_69fea24698348190b9b992a8e7cdbcd0 |
completed | May 9, 2026, 2:56 a.m. |
| PDg | Predicate description generation | batch_69fea2cfcd648190a15e5b90889095b1 |
completed | May 9, 2026, 2:58 a.m. |
Created at: April 28, 2026, 4:52 a.m.