Triple
T4912861
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lupita Nyong'o |
E110274
|
entity |
| Predicate | wrote |
P2831
|
FINISHED |
| Object | Sulwe |
E479165
|
NE 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: Sulwe | Statement: [Lupita Nyong'o, wrote, Sulwe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sulwe Context triple: [Lupita Nyong'o, wrote, Sulwe]
-
A.
Sulwe
chosen
Sulwe is a children's picture book by Lupita Nyong'o that explores colorism, self-esteem, and embracing one's own unique beauty through the story of a dark-skinned girl.
-
B.
Violet
Violet is a small, typically purple-flowered plant commonly found in temperate regions and widely recognized as a symbol of modesty and springtime.
-
C.
Violet
Violet is a character portrayed by Australian actress Robin McLeavy, likely known from her work in film or television.
-
D.
Redhead
"Redhead" is a 1959 Broadway musical comedy best known for starring dancer-actress Gwen Verdon and featuring choreography by Bob Fosse.
-
E.
Marzelline
Marzelline is a character in Beethoven's opera "Fidelio," portrayed as the jailer Rocco’s daughter who becomes romantically entangled with the disguised heroine.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69bd44132b94819088522d92beaadc78 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6e9dc41481908c0c398852e6819c |
completed | March 20, 2026, 3:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be77a1ef488190ac9cc34e67a8b243 |
completed | March 21, 2026, 10:49 a.m. |
Created at: March 20, 2026, 1:29 p.m.