Triple
T34891989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lisbeth Salander |
E1006310
|
entity |
| Predicate | fictionalTwinSibling |
P88705
|
FINISHED |
| Object | Camilla 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: Camilla Salander | Statement: [Lisbeth Salander, fictionalTwinSibling, Camilla Salander]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fictionalTwinSibling Context triple: [Lisbeth Salander, fictionalTwinSibling, Camilla Salander]
-
A.
isFictionalTwinOf
chosen
Indicates that one entity is the imagined or fictional twin counterpart of another entity, typically within a narrative or creative context.
-
B.
fictionalHalfSibling
Indicates that one entity is considered a half-sibling of another within a fictional or narrative context, sharing one parent in the story’s canon.
-
C.
fictionalBrother
Indicates that one entity is the brother of another within a fictional or imagined context.
-
D.
hasFictionalSibling
Indicates that one entity is a fictional character who is a sibling of another entity.
-
E.
fictionalCounterpartIn
Indicates that one entity serves as a fictional analogue or stand-in for another entity within a specified work or fictional universe.
- 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_69f76dbfe5788190ad8b64f241f470c8 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fed48d8e148190a99c0aea29f8a3ee |
completed | May 9, 2026, 6:30 a.m. |
| PD | Predicate disambiguation | batch_69fed3c82a24819095e614e31ac0307f |
completed | May 9, 2026, 6:27 a.m. |
Created at: May 3, 2026, 4 p.m.