Triple
T20304474
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tiger Bay |
E505571
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Anthony Dawson |
—
|
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: Anthony Dawson | Statement: [Tiger Bay, starring, Anthony Dawson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anthony Dawson Context triple: [Tiger Bay, starring, Anthony Dawson]
-
A.
Anthony Dawson
chosen
Anthony Dawson was a British character actor best known for his roles in mid-20th-century films, including notable appearances in early James Bond movies and various horror productions.
-
B.
Geoffrey Dawson
Geoffrey Dawson was a British newspaper editor and influential public figure who notably served as editor of The Times during the early 20th century.
-
C.
Douglas Dawson
Douglas Dawson was the husband of American film actress Jean Parker, known primarily in relation to her personal life.
-
D.
Gary Dawson
Gary Dawson is one of the children of British-American actor and game show host Richard Dawson.
-
E.
Frank Dawson
Frank Dawson is a character in the crime comedy film "The Switch," involved in the story's humorous and chaotic events surrounding an accidental sperm donor swap.
- 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_69e0b4b8ab648190906e18538c250148 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6773ed3248190ba949ec941e8d41f |
completed | April 20, 2026, 6:58 p.m. |
Created at: April 16, 2026, 11:17 a.m.