Triple
T32614571
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | jötnar |
E833748
|
entity |
| Predicate | relationshipWithGods |
P60881
|
FINISHED |
| Object | frequently hostile |
—
|
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: frequently hostile | Statement: [jötnar, relationshipWithGods, frequently hostile]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipWithGods Context triple: [jötnar, relationshipWithGods, frequently hostile]
-
A.
relationshipToDeities
chosen
Indicates how an entity is connected or related to one or more deities, such as through worship, lineage, role, or status.
-
B.
relatedNameOfGod
Indicates that one entity is a name, title, or designation that refers to or is associated with God.
-
C.
associatedWithGod
Indicates a relationship in which an entity is linked, related, or connected in some meaningful way to a god or deity.
-
D.
sharesDeitiesWith
Indicates that two entities have one or more deities in common within their respective religious or mythological systems.
-
E.
otherDeity
Indicates that one deity is distinct from and not identical to another deity within a given context or system.
- 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_69f3492bfa648190b6ae472074634e29 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a037cad051c8190b28b354b89208574 |
completed | May 12, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_6a0379f0cbe481909b4b8fc6cbe297f0 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:06 a.m.