Triple
T3441875
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Valkyries |
E72582
|
entity |
| Predicate | collectiveOf |
P30228
|
FINISHED |
| Object | Individual valkyrie figures such as Brynhildr |
—
|
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: Individual valkyrie figures such as Brynhildr | Statement: [Valkyries, collectiveOf, Individual valkyrie figures such as Brynhildr]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collectiveOf Context triple: [Valkyries, collectiveOf, Individual valkyrie figures such as Brynhildr]
-
A.
collectiveBody
Indicates that multiple individuals are grouped and act together as a single collective entity or body.
-
B.
usedCollectiveName
Indicates that a group of entities is referred to by a shared collective name.
-
C.
formerCollectionOf
Indicates that an entity once served as a collection or repository for another entity, but no longer holds that role.
-
D.
collectionRole
Indicates the specific function, responsibility, or position an entity holds within a collection or grouped set of items.
-
E.
isCollectionOf
chosen
Indicates that one entity is a group or aggregate composed of multiple instances or elements of another entity.
- 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_69ad85af50288190a854b76653deee6f |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adba276b708190949f294a8d09ec7b |
completed | March 8, 2026, 6:04 p.m. |
| PD | Predicate disambiguation | batch_69adae0255b48190a9069f7871c7a012 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:16 p.m.