Triple
T11793949
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jack Harbaugh |
E280457
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Harbaugh
Harbaugh is a notable American family name most prominently associated with football coaches Jack, Jim, and John Harbaugh.
|
E280457
|
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: Harbaugh | Statement: [Jack Harbaugh, familyName, Harbaugh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harbaugh Context triple: [Jack Harbaugh, familyName, Harbaugh]
-
A.
Rhule
Rhule is the surname of American football coach Matt Rhule, known for his collegiate and NFL head coaching roles.
-
B.
Jack Harbaugh
Jack Harbaugh is an American former college football coach best known for his long coaching career and as the patriarch of the Harbaugh football family, including sons Jim and John Harbaugh.
-
C.
Dilfer
Dilfer is the surname of former NFL quarterback and Super Bowl champion Trent Dilfer.
-
D.
Carl Harbaugh
Carl Harbaugh was an American actor and filmmaker active in the early 20th century, known for his roles in silent films.
-
E.
Jim Harbaugh
Jim Harbaugh is an American football coach and former NFL quarterback known for leading both college and professional teams to national prominence, including successful stints with Stanford, the San Francisco 49ers, and the University of Michigan.
- 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: Harbaugh Triple: [Jack Harbaugh, familyName, Harbaugh]
Generated description
Harbaugh is a notable American family name most prominently associated with football coaches Jack, Jim, and John Harbaugh.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Harbaugh Target entity description: Harbaugh is a notable American family name most prominently associated with football coaches Jack, Jim, and John Harbaugh.
-
A.
Rhule
Rhule is the surname of American football coach Matt Rhule, known for his collegiate and NFL head coaching roles.
-
B.
Jack Harbaugh
chosen
Jack Harbaugh is an American former college football coach best known for his long coaching career and as the patriarch of the Harbaugh football family, including sons Jim and John Harbaugh.
-
C.
Dilfer
Dilfer is the surname of former NFL quarterback and Super Bowl champion Trent Dilfer.
-
D.
Carl Harbaugh
Carl Harbaugh was an American actor and filmmaker active in the early 20th century, known for his roles in silent films.
-
E.
Jim Harbaugh
Jim Harbaugh is an American football coach and former NFL quarterback known for leading both college and professional teams to national prominence, including successful stints with Stanford, the San Francisco 49ers, and the University of Michigan.
- F. None of above.
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_69d6ab258b808190b1735835c841e3a4 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a5a082d08190a42541396a06ed98 |
completed | April 10, 2026, 7:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f09115c66c8190b0a3e775bdf575c1 |
completed | April 28, 2026, 10:51 a.m. |
| NEDg | Description generation | batch_69f0bd40108c8190863a60cf01cc7201 |
completed | April 28, 2026, 1:59 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f0ef7e9f388190b33f6c16abadfde9 |
completed | April 28, 2026, 5:33 p.m. |
Created at: April 8, 2026, 9:42 p.m.