Triple
T14300660
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Purves |
E354552
|
entity |
| Predicate | portrayedCharacter |
P1668
|
FINISHED |
| Object | Steven Taylor |
E354551
|
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: Steven Taylor | Statement: [Peter Purves, portrayedCharacter, Steven Taylor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Steven Taylor Context triple: [Peter Purves, portrayedCharacter, Steven Taylor]
-
A.
Steven Taylor
chosen
Steven Taylor is a companion of the First Doctor in the classic British science fiction television series Doctor Who.
-
B.
Alex Taylor
Alex Taylor is a member of the Taylor family and the sibling of renowned singer-songwriter James Taylor.
-
C.
Lee Humphrey
Lee Humphrey is an American former college basketball guard best known as a sharpshooting three-point specialist for the University of Florida's back-to-back national championship teams in the mid-2000s.
-
D.
Douglas Shearer
Douglas Shearer was a pioneering Canadian-American sound engineer and special effects designer in Hollywood, renowned for his groundbreaking work at MGM and multiple Academy Awards.
-
E.
Ian Breakwell
Ian Breakwell was a British artist and diarist known for his observational writings, experimental films, and conceptual artworks that documented everyday life.
- 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_69d8278e17088190b328c5a9d4be74ff |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de717e246c819083e67ac2b3b77881 |
completed | April 14, 2026, 4:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd5bb9947481909cd16aa1d719fbe5 |
completed | May 8, 2026, 3:42 a.m. |
Created at: April 10, 2026, 1:11 a.m.