Triple
T806839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Loganair |
E17455
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
Willie Logan
Willie Logan was a Scottish entrepreneur best known for establishing the regional airline Loganair.
|
E112046
|
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: Willie Logan | Statement: [Loganair, foundedBy, Willie Logan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Willie Logan Context triple: [Loganair, foundedBy, Willie Logan]
-
A.
Shawn Hochuli
Shawn Hochuli is an American NFL official who followed his father Ed Hochuli into a prominent career as a referee.
-
B.
Leon Riley
Leon Riley was an American professional baseball player and minor league manager, best known as the father of legendary NBA coach and executive Pat Riley.
-
C.
Mancel Warrick
Mancel Warrick was the father of American soul and R&B singer Dee Dee Warwick and a member of the musical Warwick family.
-
D.
Grady Lewis
Grady Lewis was an American basketball coach and former player best known for his role in early professional basketball, including coaching in the Basketball Association of America/NBA era.
-
E.
Woody Bledsoe
Woody Bledsoe was an American mathematician and computer scientist recognized as a pioneer in artificial intelligence, particularly in automated theorem proving and pattern recognition.
- 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: Willie Logan Triple: [Loganair, foundedBy, Willie Logan]
Generated description
Willie Logan was a Scottish entrepreneur best known for establishing the regional airline Loganair.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Willie Logan Target entity description: Willie Logan was a Scottish entrepreneur best known for establishing the regional airline Loganair.
-
A.
Shawn Hochuli
Shawn Hochuli is an American NFL official who followed his father Ed Hochuli into a prominent career as a referee.
-
B.
Leon Riley
Leon Riley was an American professional baseball player and minor league manager, best known as the father of legendary NBA coach and executive Pat Riley.
-
C.
Mancel Warrick
Mancel Warrick was the father of American soul and R&B singer Dee Dee Warwick and a member of the musical Warwick family.
-
D.
Grady Lewis
Grady Lewis was an American basketball coach and former player best known for his role in early professional basketball, including coaching in the Basketball Association of America/NBA era.
-
E.
Woody Bledsoe
Woody Bledsoe was an American mathematician and computer scientist recognized as a pioneer in artificial intelligence, particularly in automated theorem proving and pattern recognition.
- 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_69a4937ae8a08190b5084a03d532b30e |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4aac1142881908f6f78bfdb887930 |
completed | March 1, 2026, 9:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a93395f2d8819082d622d1d6415073 |
completed | March 5, 2026, 7:41 a.m. |
| NEDg | Description generation | batch_69a974b2e084819082a46e24dd67e852 |
completed | March 5, 2026, 12:18 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69a975517db48190b73e0c54ee1f6d60 |
completed | March 5, 2026, 12:21 p.m. |
Created at: March 1, 2026, 7:38 p.m.