Triple
T23430689
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dingiswayo |
E563319
|
entity |
| Predicate | predecessor |
P97
|
FINISHED |
| Object | Jobe kaKhayi |
—
|
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: Jobe kaKhayi | Statement: [Dingiswayo, predecessor, Jobe kaKhayi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jobe kaKhayi Context triple: [Dingiswayo, predecessor, Jobe kaKhayi]
-
A.
Jobe kaKhayi
chosen
Jobe kaKhayi was a prominent Zulu leader and king of the Mthethwa people in the late 18th and early 19th centuries, known for consolidating power in the region prior to Shaka Zulu’s rise.
-
B.
Kazi Hayat
Kazi Hayat is a prominent Bangladeshi film director, screenwriter, and actor known for his influential contributions to commercial Bengali cinema.
-
C.
Sajibu
Sajibu is the first month of the traditional Meitei lunar calendar, marking the beginning of the new year in Manipur.
-
D.
N'Jobu
N'Jobu is a Wakandan prince and undercover War Dog operative, best known as Erik Killmonger's father in the Marvel Cinematic Universe.
-
E.
Kijitonyama
Kijitonyama is a residential and commercial neighborhood in Dar es Salaam, Tanzania, known as one of the urban wards within the Kinondoni District.
- 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_69e24553980c8190bb66a2ae0bdab125 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f1a5d8130881909e4f3455afef1804 |
completed | April 29, 2026, 6:31 a.m. |
Created at: April 17, 2026, 5:48 p.m.