Triple
T18762562
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wes Brown |
E458808
|
entity |
| Predicate | fullName |
P16
|
FINISHED |
| Object |
Wesley Michael Brown
Wesley Michael Brown is an English former professional footballer best known for his long tenure as a defender with Manchester United and the England national team.
|
E1343607
|
NE FINISHED |
How this triple was built (4 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: Wesley Michael Brown | Statement: [Wes Brown, fullName, Wesley Michael Brown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wesley Michael Brown Context triple: [Wes Brown, fullName, Wesley Michael Brown]
-
A.
Wes Peters
Wes Peters was an American architect closely associated with Frank Lloyd Wright, known for his structural engineering work on many of Wright’s major projects.
-
B.
Cal Hudson
Cal Hudson is a Starfleet officer in the Star Trek universe who defects to join the Maquis resistance movement against the Cardassians.
-
C.
Joshua Lewis
Joshua Lewis is a personal name shared by multiple individuals, including professionals and public figures in various fields.
-
D.
Jesse Woods
Jesse Woods is an American singer-songwriter known for his atmospheric, folk-influenced indie music.
-
E.
Wesley LaRue
Wesley LaRue is an individual notable enough to be recognized as a namesake of the surname LaRue.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Wesley Michael Brown Triple: [Wes Brown, fullName, Wesley Michael Brown]
Generated description
Wesley Michael Brown is an English former professional footballer best known for his long tenure as a defender with Manchester United and the England national team.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Wesley Michael Brown Target entity description: Wesley Michael Brown is an English former professional footballer best known for his long tenure as a defender with Manchester United and the England national team.
-
A.
Wes Peters
Wes Peters was an American architect closely associated with Frank Lloyd Wright, known for his structural engineering work on many of Wright’s major projects.
-
B.
Cal Hudson
Cal Hudson is a Starfleet officer in the Star Trek universe who defects to join the Maquis resistance movement against the Cardassians.
-
C.
Joshua Lewis
Joshua Lewis is a personal name shared by multiple individuals, including professionals and public figures in various fields.
-
D.
Jesse Woods
Jesse Woods is an American singer-songwriter known for his atmospheric, folk-influenced indie music.
-
E.
Wesley LaRue
Wesley LaRue is an individual notable enough to be recognized as a namesake of the surname LaRue.
- F. None of above. chosen
Provenance (5 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_69d8d395dba0819087568404508590cb |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e58d80a954819083946dafc0c7af05 |
completed | April 20, 2026, 2:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a054710894c819097fc5cd9753a9c94 |
completed | May 14, 2026, 3:52 a.m. |
| NEDg | Description generation | batch_6a054b1a8698819090e8594f00588703 |
completed | May 14, 2026, 4:10 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a054b881bd48190ab3ae42719357d7c |
completed | May 14, 2026, 4:11 a.m. |
Created at: April 10, 2026, 11:52 a.m.