Triple
T20286839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kathy Lette |
E509902
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Geoffrey Robertson |
—
|
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: Geoffrey Robertson | Statement: [Kathy Lette, spouse, Geoffrey Robertson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Geoffrey Robertson Context triple: [Kathy Lette, spouse, Geoffrey Robertson]
-
A.
Geoffrey Robertson
chosen
Geoffrey Robertson is a prominent British-Australian human rights barrister, academic, and broadcaster known for his work on international justice and civil liberties.
-
B.
Michael Kirby
Michael Kirby was an American actor and figure skater known for appearing in mid-20th-century films and stage productions.
-
C.
Duncan Kennedy
Duncan Kennedy is a screenwriter best known for co-writing the 1999 science fiction horror film "Deep Blue Sea."
-
D.
Tristan Goligher
Tristan Goligher is a British film producer known for acclaimed independent features such as "45 Years" and "Lean on Pete."
-
E.
Dominic Grieve
Dominic Grieve is a British barrister and former Conservative Member of Parliament who served as Attorney General for England and Wales from 2010 to 2014.
- 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_69e0b4c652388190b782cad965e5a098 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e676931fe08190b278d829a745701f |
completed | April 20, 2026, 6:55 p.m. |
Created at: April 16, 2026, 11:06 a.m.