Triple
T10465078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | How to Be Good |
E246772
|
entity |
| Predicate | protagonist |
P268
|
FINISHED |
| Object | Katie Carr |
E925362
|
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: Katie Carr | Statement: [How to Be Good, protagonist, Katie Carr]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Katie Carr Context triple: [How to Be Good, protagonist, Katie Carr]
-
A.
Katie Carr
chosen
Katie Carr is the conflicted, self-critical doctor and wife who narrates Nick Hornby’s novel "How to Be Good," exploring themes of morality, marriage, and modern middle-class guilt.
-
B.
Katie McNeil
Katie McNeil is an American talent manager best known for her work in the music industry and for being married to singer-songwriter Neil Diamond.
-
C.
Katie Boyle
Katie Boyle was an Italian-born British television presenter and actress best known for hosting the Eurovision Song Contest multiple times in the 1960s and 1970s.
-
D.
Katie Luber
Katie Luber is an American art museum director and curator known for leading major institutions, including the Minneapolis Institute of Art.
-
E.
Katie King
Katie King is the daughter of British television presenter and former "Countdown" co-host Carol Vorderman.
- 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_69d381c16c248190a2fe5b471e584e9c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d50886c2a8819086da6c08356ec6bf |
completed | April 7, 2026, 1:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e5e877c6188190817fb30f2c9a07bf |
completed | April 20, 2026, 8:48 a.m. |
Created at: April 6, 2026, 12:19 p.m.