Triple
T18352337
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Love (novel) |
E439698
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Junior Viviane |
—
|
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: Junior Viviane | Statement: [Love (novel), mainCharacter, Junior Viviane]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Junior Viviane Context triple: [Love (novel), mainCharacter, Junior Viviane]
-
A.
Junior Viviane
chosen
Junior Viviane is a fictional character appearing in Toni Morrison’s novel "Love."
-
B.
Vivianne
Vivianne is a Dutch professional footballer best known as one of the most prolific forwards in women’s football, starring for Arsenal and the Netherlands national team.
-
C.
Vivian
Vivian is an English surname historically associated with British nobility and notable figures in politics, the military, and the arts.
-
D.
Vivian
Vivian is the given name of A. V. Hill, the Nobel Prize–winning British physiologist and biophysicist known for his pioneering work on muscle physiology and heat production.
-
E.
Vivian
"Vivian" is a song by the American nerd rock band Nerf Herder, known for their humorous and pop-culture-laden style.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b918221c8190a9f7b563d64ac677 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e514f8f07c8190a1506d4a327369d0 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 10:37 a.m.