Triple
T14765147
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bosch |
E346973
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Harry Bosch |
E379930
|
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: Harry Bosch | Statement: [Bosch, mainCharacter, Harry Bosch]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harry Bosch Context triple: [Bosch, mainCharacter, Harry Bosch]
-
A.
Harry Bosch
chosen
Harry Bosch is a hard-boiled Los Angeles homicide detective and the central protagonist of Michael Connelly’s long-running crime novel series.
-
B.
Harry Block
Harry Block is the neurotic, self-absorbed writer protagonist of Woody Allen’s film "Deconstructing Harry," whose chaotic personal life fuels his fiction.
-
C.
Ed McBain
Ed McBain was the pen name of American author Evan Hunter, best known for his influential 87th Precinct police procedural novels and his significant impact on modern crime fiction.
-
D.
Inspector Harry Callahan
Inspector Harry Callahan is a tough, no-nonsense San Francisco police detective famously portrayed by Clint Eastwood in the Dirty Harry film series.
-
E.
Frank Roarke
Frank Roarke is a veteran, morally ambiguous LAPD detective who mentors a rookie cop in the television adaptation of "Training Day."
- 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_69d822e8896c819091169882f9b20486 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69dec7f576c881909da70627f5897c94 |
completed | April 14, 2026, 11:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe0cf4cef081909fa62125f43b36bc |
completed | May 8, 2026, 4:19 p.m. |
Created at: April 10, 2026, 1:30 a.m.