Triple
T20269598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rafiki |
E499058
|
entity |
| Predicate | affiliation |
P10
|
FINISHED |
| Object | Simba |
—
|
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: Simba | Statement: [Rafiki, affiliation, Simba]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Simba Context triple: [Rafiki, affiliation, Simba]
-
A.
Simba
chosen
Simba is the lion prince who becomes king in Disney's animated film "The Lion King," known for his journey from guilt-ridden exile to courageous leader.
-
B.
Simba
Simba is the stage name of Tanzanian singer and songwriter Diamond Platnumz, a leading figure in contemporary Bongo Flava and East African pop music.
-
C.
Maxwell Simba
Maxwell Simba is a Kenyan actor best known for his lead role as William Kamkwamba in the film "The Boy Who Harnessed the Wind."
-
D.
Mufasa
Mufasa is the wise and noble lion king of the Pride Lands and father of Simba in Disney's The Lion King.
-
E.
Shenzi
Shenzi is a cunning hyena and one of the primary antagonists in Disney's "The Lion King," known for serving as a key henchman to Scar.
- 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_69da6275fa6c8190952924930adee150 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e675dc8e708190b840d687f134c9e8 |
completed | April 20, 2026, 6:52 p.m. |
Created at: April 11, 2026, 11:42 p.m.