Triple
T17861922
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ivan Tors Films |
E446093
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Daktari |
—
|
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: Daktari | Statement: [Ivan Tors Films, notableWork, Daktari]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Daktari Context triple: [Ivan Tors Films, notableWork, Daktari]
-
A.
Daktari
chosen
Daktari is a 1960s American television drama series set in East Africa that follows a veterinarian and his team as they care for wild animals at a fictional wildlife preserve.
-
B.
Docter
Docter is the surname of Pete Docter, the acclaimed American animator, director, and key creative figure at Pixar Animation Studios.
-
C.
Doctores
Doctores is a Mexico City Metro station on Line 8 serving the Doctores neighborhood near the city center.
-
D.
La Dotta
La Dotta is a nickname for the Italian city of Bologna, highlighting its historic role as a major center of learning and home to one of the world’s oldest universities.
-
E.
Doctor Doctor
Doctor Doctor is an Australian television drama series centered on a charismatic but troubled heart surgeon who is forced to return to practice in his rural hometown.
- 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_69d8b9f26f18819089c9e43250bee6ae |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e49790ea148190b7a966812d44f430 |
completed | April 19, 2026, 8:51 a.m. |
Created at: April 10, 2026, 10:17 a.m.