Triple
T20241916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Babylon 5 |
E498316
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Susan Ivanova |
—
|
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: Susan Ivanova | Statement: [Babylon 5, mainCharacter, Susan Ivanova]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Susan Ivanova Context triple: [Babylon 5, mainCharacter, Susan Ivanova]
-
A.
Natalya Ivanova
Natalya Ivanova is a film producer known for her work on the movie "Two Women."
-
B.
Valentina Serova
Valentina Serova was the mother of renowned Russian painter Valentin Serov and a notable Russian pianist and composer in her own right.
-
C.
Ivanova
chosen
Ivanova is a common Slavic surname, particularly prevalent in Russia and other Eastern European countries, typically indicating female lineage from someone named Ivan.
-
D.
Helena Rozhenko
Helena Rozhenko is a human woman in the Star Trek universe best known as the adoptive mother of the Klingon Starfleet officer Worf.
-
E.
Anya Amasova
Anya Amasova is a Soviet KGB agent and Bond girl featured in the James Bond film "The Spy Who Loved Me."
- 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_69da6274c58c81909c646eabed6f4f30 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6716f9d248190a145f6883827ebbe |
completed | April 20, 2026, 6:33 p.m. |
Created at: April 11, 2026, 11:40 p.m.