Triple
T15897964
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Angela Sarafyan |
E385511
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Nikita |
E498068
|
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: Nikita | Statement: [Angela Sarafyan, notableWork, Nikita]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nikita Context triple: [Angela Sarafyan, notableWork, Nikita]
-
A.
Nikita
Nikita is a given name most famously associated with Soviet leader Nikita Khrushchev.
-
B.
Nikita
chosen
Nikita is an American action-thriller television series centered on a rogue assassin seeking to dismantle the secret government organization that trained her.
-
C.
La Femme Nikita
La Femme Nikita is a Canadian television drama series about a convicted criminal forced to work as an assassin for a secret government organization.
-
D.
Little Nikita
Little Nikita is a 1988 American thriller film starring River Phoenix and Sidney Poitier that blends coming-of-age drama with Cold War espionage.
-
E.
Nikita Unfiltered
Nikita Unfiltered is a reality web series following beauty influencer Nikita Dragun’s personal and professional life.
- 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_69d86da5b800819083a31be937d738b0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1563b0e4c8190b338672dfb122665 |
completed | April 16, 2026, 9:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb04d4d1c819091d9b3357ca0deca |
completed | May 9, 2026, 10:08 p.m. |
Created at: April 10, 2026, 4:51 a.m.