Triple
T14239957
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Last Tango in Halifax |
E352978
|
entity |
| Predicate | executiveProducer |
P7225
|
FINISHED |
| Object | Matthew Read |
E867801
|
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: Matthew Read | Statement: [Last Tango in Halifax, executiveProducer, Matthew Read]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matthew Read Context triple: [Last Tango in Halifax, executiveProducer, Matthew Read]
-
A.
Matthew Read
chosen
Matthew Read is a British television producer and writer known for his work on acclaimed drama series and films.
-
B.
Matthew Skemp
Matthew Skemp is a musician best known as a member of the experimental indie rock band Volcano Choir.
-
C.
Matthew Skemp
Matthew Skemp is a musician best known as a member of the experimental indie rock band Collections of Colonies of Bees.
-
D.
Matthew Skemp
Matthew Skemp is a contributor to the project or work titled "Unmap," likely involved in its creation or development.
-
E.
Rory Read
Rory Read is a technology executive best known for serving as CEO of Advanced Micro Devices (AMD) and holding senior leadership roles at major tech companies.
- 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_69d8278adc7c8190a9218d69bce3c4e6 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de62432fb48190b153805b85c4f2d2 |
completed | April 14, 2026, 3:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd282183308190b63172972773b3c2 |
completed | May 8, 2026, 12:02 a.m. |
Created at: April 10, 2026, 1:08 a.m.