Triple
T10850692
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | R. B. Kitaj |
E256134
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Lem Dobbs |
E456434
|
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: Lem Dobbs | Statement: [R. B. Kitaj, child, Lem Dobbs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lem Dobbs Context triple: [R. B. Kitaj, child, Lem Dobbs]
-
A.
Lem Dobbs
chosen
Lem Dobbs is a British-American screenwriter known for his work on films such as "Dark City," "The Limey," and "The Score."
-
B.
James Marr
James Marr is a relatively obscure individual whose primary distinction is sharing the surname associated with the better-known Marr family name.
-
C.
Alan Coren
Alan Coren was a British humorist, satirist, and longtime Punch magazine editor known for his witty columns, books, and frequent appearances on radio and television panel shows.
-
D.
Andrew Neil
Andrew Neil is a veteran British journalist and broadcaster known for his incisive political interviews and leadership roles at major UK media outlets.
-
E.
Jeremy Paxman
Jeremy Paxman is a British broadcaster, journalist, and author best known for his incisive interviewing style on BBC’s Newsnight and as the long-time host of the quiz show University Challenge.
- 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_69d6aa81a5d08190aa86689061d1ddd2 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d75116af20819084c7f8fa88d18e61 |
completed | April 9, 2026, 7:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e23b8b3fd48190b36e34dc19fa5193 |
completed | April 17, 2026, 1:54 p.m. |
Created at: April 8, 2026, 9:20 p.m.