Triple
T2245763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Queen |
E49499
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Andy Harries |
E203213
|
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: Andy Harries | Statement: [The Queen, producer, Andy Harries]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andy Harries Context triple: [The Queen, producer, Andy Harries]
-
A.
Andy Harries
chosen
Andy Harries is a British television producer best known as the co-founder of Left Bank Pictures and for producing acclaimed dramas such as The Crown.
-
B.
Mark Herron
Mark Herron was an American actor best known for being the fourth husband of legendary entertainer Judy Garland.
-
C.
Matt Hulett
Matt Hulett is an American technology and business executive known for leading and scaling multiple software and digital media companies.
-
D.
Bruce Harrell
Bruce Harrell is an American politician and attorney serving as the mayor of Seattle, known for his long tenure on the Seattle City Council and focus on public safety and police reform.
-
E.
Rich Harris
Rich Harris is a software engineer and journalist best known for creating the Svelte JavaScript framework and his work on interactive data visualizations.
- 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_69a88aa979788190ad6500f1d8eee2fc |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc0ea75d881909d4e176a432f32e8 |
completed | March 7, 2026, 6:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69aea86527d08190a1332d133fbd7293 |
completed | March 9, 2026, 11 a.m. |
Created at: March 4, 2026, 7:47 p.m.