Triple
T34875598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vanger family mystery |
E1005872
|
entity |
| Predicate | centralCharacterInvolved |
P9202
|
FINISHED |
| Object | Lisbeth Salander |
—
|
NE NERFINISHED |
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: Lisbeth Salander | Statement: [Vanger family mystery, centralCharacterInvolved, Lisbeth Salander]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: centralCharacterInvolved Context triple: [Vanger family mystery, centralCharacterInvolved, Lisbeth Salander]
-
A.
constantInvolved
Indicates that a constant participates in or is directly involved in the specified relation, operation, or context.
-
B.
antagonistInvolved
Indicates that an antagonist participates in, influences, or is otherwise actively involved in the referenced event or situation.
-
C.
laterMainCharacterOf
Indicates that one entity becomes the main character of a work at a later point in time, succeeding another main character.
-
D.
mainCharactersAre
Indicates that the specified entities serve as the primary or central characters in a narrative or work.
-
E.
mainProtagonist
chosen
Indicates that the subject is the central character or primary focus in the narrative of the related work.
- 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_69f76dbde1c08190a24e7f9beb564c8d |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fd7fdafbe881908a31fcb407af2c34 |
completed | May 8, 2026, 6:16 a.m. |
| PD | Predicate disambiguation | batch_69fd7ef0ea908190b5d83f71565bdb1c |
completed | May 8, 2026, 6:13 a.m. |
Created at: May 3, 2026, 4 p.m.