Triple
T1844730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Follow a Star |
E41258
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Richard Wattis |
E213947
|
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: Richard Wattis | Statement: [Follow a Star, starring, Richard Wattis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Richard Wattis Context triple: [Follow a Star, starring, Richard Wattis]
-
A.
Richard Wattis
chosen
Richard Wattis was a British character actor known for his dry, officious comedic roles in mid-20th-century films and television.
-
B.
Richard Hiscott
Richard Hiscott is an editor known for his work on the television series "Willow."
-
C.
Richard Bristow
Richard Bristow was a 16th-century English Catholic scholar and theologian who contributed to the development and annotation of the Douay–Rheims Bible.
-
D.
John Watts
John Watts was an 18th-century London printer and publisher known for producing notable literary and theatrical works.
-
E.
David Ewart
David Ewart was a prominent early 20th-century Canadian architect best known for designing major federal buildings in Ottawa, including landmark public institutions.
- 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_69a88648cd44819093303206d96d76ad |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb04fe9d481909b5c1973d3f9b92d |
completed | March 7, 2026, 4:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae516ffd088190ae2c730e1caff8f6 |
completed | March 9, 2026, 4:49 a.m. |
Created at: March 4, 2026, 7:33 p.m.