Triple
T13700193
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jack Traven |
E328494
|
entity |
| Predicate | partner |
P1136
|
FINISHED |
| Object | Harry Temple |
E823705
|
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 Temple | Statement: [Jack Traven, partner, Harry Temple]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harry Temple Context triple: [Jack Traven, partner, Harry Temple]
-
A.
Harry Temple
chosen
Harry Temple is a seasoned Los Angeles police officer and bomb squad veteran who serves as Jack Traven’s mentor and partner in the action film "Speed."
-
B.
Henry Maudsley
Henry Maudsley was a pioneering 19th-century British psychiatrist whose work and philanthropy significantly shaped modern mental health care and psychiatric institutions.
-
C.
Frank Campion
Frank Campion is a Canadian municipal politician who serves as the mayor of Welland, Ontario.
-
D.
Hugo Davenport
Hugo Davenport is the son of English actor Nigel Davenport, known primarily in relation to his father's prominence in British film and television.
-
E.
Dr. James Mortimer
Dr. James Mortimer is a country doctor and friend of the Baskerville family who seeks Sherlock Holmes’s help in Arthur Conan Doyle’s novel "The Hound of the Baskervilles."
- 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_69d8076ff62081908a7bd79889edd7a0 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc879adc88190b03f1cf815b71061 |
completed | April 12, 2026, 4:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f794575d3881908de6ed988d848918 |
completed | May 3, 2026, 6:30 p.m. |
Created at: April 9, 2026, 9:54 p.m.