Triple
T17320391
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeremy Paxman |
E420543
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Paxman |
E420543
|
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: Paxman | Statement: [Jeremy Paxman, familyName, Paxman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paxman Context triple: [Jeremy Paxman, familyName, Paxman]
-
A.
Paxman
chosen
Paxman is a British surname most prominently associated with Jeremy Paxman, the veteran broadcaster and former host of the quiz show "University Challenge."
-
B.
Lord & Hewlett
Lord & Hewlett was an American architectural firm active in the early 20th century, known for designing significant public and institutional buildings.
-
C.
Harman
Harman is a given name and surname used in various cultures, often considered a variant of the name Hermann.
-
D.
Ferranti
Ferranti was a pioneering British electrical engineering and computer company known for its early work in power systems and some of the first commercial computers.
-
E.
Baird
Baird is a Scottish surname most famously associated with John Logie Baird, a pioneer of early television technology.
- 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_69d889d22b848190a4663d0b8f8f76e7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e439a066b481908e8aee1885809eba |
completed | April 19, 2026, 2:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a018c483e988190a481b4c487f79329 |
completed | May 11, 2026, 7:59 a.m. |
Created at: April 10, 2026, 5:43 a.m.