Triple
T9090056
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | D. E. Hughes |
E217857
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | David Edward Hughes |
E214376
|
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: David Edward Hughes | Statement: [D. E. Hughes, name, David Edward Hughes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Edward Hughes Context triple: [D. E. Hughes, name, David Edward Hughes]
-
A.
David Edward Hughes
chosen
David Edward Hughes was a 19th-century British inventor and physicist best known for pioneering work in telegraphy, the carbon microphone, and early radio wave detection.
-
B.
David A. Hughes
David A. Hughes is a British composer and musician best known for his film and television scores.
-
C.
Mark R. Hughes
Mark R. Hughes was an American entrepreneur best known as the founder and driving force behind the global nutrition and weight-management company Herbalife.
-
D.
Patrick Hughes
Patrick Hughes is an Australian film director best known for helming action movies such as *The Expendables 3* and *The Hitman's Bodyguard*.
-
E.
Jimmy Hughes
Jimmy Hughes is a central character on the sitcom "Yes, Dear," portrayed as a well-meaning but often overwhelmed young father and husband navigating everyday family chaos.
- 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_69ca83d8ab5881909d8fddae363b32b1 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc965971f88190acffbf204c11832b |
completed | April 1, 2026, 3:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0478fc0c4819090de2b761804166f |
completed | April 3, 2026, 11:04 p.m. |
Created at: March 30, 2026, 7:14 p.m.