Triple
T21892411
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Studebaker Lark |
E540584
|
entity |
| Predicate | designer |
P184
|
FINISHED |
| Object |
Duncan McRae
Duncan McRae was an American automotive designer best known for his influential work on mid-20th-century Studebaker models.
|
E1511979
|
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: Duncan McRae | Statement: [Studebaker Lark, designer, Duncan McRae]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Duncan McRae Context triple: [Studebaker Lark, designer, Duncan McRae]
-
A.
Ian MacDougall
Ian MacDougall is a guitarist best known for his work with the Texas punk rock band The Riverboat Gamblers.
-
B.
Duncan Stewart
Duncan Stewart is a music producer best known for his work on U2’s album "Songs of Surrender."
-
C.
Duncan Stewart
Duncan Stewart is a member of the band Basement, contributing to the English rock group's distinctive alternative and emo-influenced sound.
-
D.
Duncan Stewart
Duncan Stewart was a historical figure significant enough in Tennessee's early history that Stewart County was named in his honor, likely reflecting his role as a prominent local leader or public official.
-
E.
Duncan Fraser
Duncan Fraser is a Canadian actor best known for his role in the cult psychological horror film "The Reflecting Skin."
- 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: Duncan McRae Triple: [Studebaker Lark, designer, Duncan McRae]
Generated description
Duncan McRae was an American automotive designer best known for his influential work on mid-20th-century Studebaker models.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Duncan McRae Target entity description: Duncan McRae was an American automotive designer best known for his influential work on mid-20th-century Studebaker models.
-
A.
Ian MacDougall
Ian MacDougall is a guitarist best known for his work with the Texas punk rock band The Riverboat Gamblers.
-
B.
Duncan Stewart
Duncan Stewart is a member of the band Basement, contributing to the English rock group's distinctive alternative and emo-influenced sound.
-
C.
Duncan Stewart
Duncan Stewart is a music producer best known for his work on U2’s album "Songs of Surrender."
-
D.
Duncan Stewart
Duncan Stewart was a historical figure significant enough in Tennessee's early history that Stewart County was named in his honor, likely reflecting his role as a prominent local leader or public official.
-
E.
Duncan Fraser
Duncan Fraser is a Canadian actor best known for his role in the cult psychological horror film "The Reflecting Skin."
- 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_69e0c47a95908190ae3e19b716accb3d |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f11fc46dd481908a119cfbe26564a3 |
completed | April 28, 2026, 8:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a6d676e7c8190a6ee299393a147cc |
completed | May 18, 2026, 1:37 a.m. |
| NEDg | Description generation | batch_6a0a6e18d4f48190bfb917c9c9109ea5 |
completed | May 18, 2026, 1:40 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a6ee56684819082d2001b2e817ed8 |
completed | May 18, 2026, 1:44 a.m. |
Created at: April 16, 2026, 7:06 p.m.