Triple
T10627160
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Freki |
E250352
|
entity |
| Predicate | hasCompanionRole |
P22642
|
FINISHED |
| Object | follows Odin into battle |
—
|
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: follows Odin into battle | Statement: [Freki, hasCompanionRole, follows Odin into battle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCompanionRole Context triple: [Freki, hasCompanionRole, follows Odin into battle]
-
A.
hasCompanionCandidate
Indicates that an entity is associated with another entity that is being considered or proposed as a potential companion.
-
B.
hasCompanionPiece
Indicates that one item is conceptually or functionally paired with another item as its companion piece.
-
C.
hasCompanionPillar
Indicates that an entity is associated with or supported by a corresponding companion pillar.
-
D.
companionOf
chosen
Indicates that one entity serves as a companion or partner to another, typically accompanying or being closely associated with them.
-
E.
hasAuxiliaryRole
Indicates that an entity serves in a supporting or secondary capacity to another entity or primary role.
- 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_69d6aa5993448190a493b790b8f85010 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6df8207f08190a6362a8ba00988b2 |
completed | April 8, 2026, 11:06 p.m. |
| PD | Predicate disambiguation | batch_69d6dd7fae088190973f70c69738af49 |
completed | April 8, 2026, 10:58 p.m. |
Created at: April 8, 2026, 8:55 p.m.