Triple
T23389108
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Goodbye World |
E593963
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Kerry Bishé |
—
|
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: Kerry Bishé | Statement: [Goodbye World, starring, Kerry Bishé]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kerry Bishé Context triple: [Goodbye World, starring, Kerry Bishé]
-
A.
Kerry Bishé
chosen
Kerry Bishé is a New Zealand–born American actress best known for her roles in the film "Argo" and the television series "Halt and Catch Fire."
-
B.
Tania Tapsell
Tania Tapsell is a New Zealand politician and local government leader known for serving as the mayor of Rotorua and for her prominence as a young Māori woman in public office.
-
C.
Claire Jackman
Claire Jackman is a fictional character portrayed by actress Gina Bellman, known from her work in British television and film.
-
D.
Robyn Nevin
Robyn Nevin is a prominent Australian actress and theatre director known for her extensive work on stage, film, and television, as well as her leadership roles in major Australian theatre companies.
-
E.
Kate Mulvany
Kate Mulvany is an Australian actress, playwright, and screenwriter known for her work across theatre, film, and television.
- 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_69e25d2754fc819085deea939bde60ab |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a49a7c14819082aab826715976c5 |
completed | April 29, 2026, 6:26 a.m. |
Created at: April 17, 2026, 5:35 p.m.