Triple
T4481477
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Travis Kelce |
E100143
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object |
Donna Kelce
Donna Kelce is the mother of NFL stars Travis and Jason Kelce, known for her prominent and enthusiastic presence supporting both sons’ teams.
|
E443796
|
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: Donna Kelce | Statement: [Travis Kelce, relative, Donna Kelce]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Donna Kelce Context triple: [Travis Kelce, relative, Donna Kelce]
-
A.
Pattie Mallette
Pattie Mallette is a Canadian author and film producer best known as the mother of pop singer Justin Bieber.
-
B.
Kim Burrell
Kim Burrell is an American gospel singer renowned for her virtuosic, jazz-influenced vocal style and influential work in contemporary gospel music.
-
C.
Pam Bryant
Pam Bryant is an American woman best known as the mother of the late NBA superstar Kobe Bryant.
-
D.
Ingrid Harbaugh
Ingrid Harbaugh is the wife of longtime Baltimore Ravens head coach John Harbaugh and is known for her involvement in charitable and community activities connected to the team.
-
E.
Robin Lynn Macy
Robin Lynn Macy is an American musician and singer best known as a founding member and early guitarist of the country music group that became the Dixie Chicks.
- 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: Donna Kelce Triple: [Travis Kelce, relative, Donna Kelce]
Generated description
Donna Kelce is the mother of NFL stars Travis and Jason Kelce, known for her prominent and enthusiastic presence supporting both sons’ teams.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Donna Kelce Target entity description: Donna Kelce is the mother of NFL stars Travis and Jason Kelce, known for her prominent and enthusiastic presence supporting both sons’ teams.
-
A.
Pattie Mallette
Pattie Mallette is a Canadian author and film producer best known as the mother of pop singer Justin Bieber.
-
B.
Kim Burrell
Kim Burrell is an American gospel singer renowned for her virtuosic, jazz-influenced vocal style and influential work in contemporary gospel music.
-
C.
Pam Bryant
Pam Bryant is an American woman best known as the mother of the late NBA superstar Kobe Bryant.
-
D.
Alison Harbaugh
Alison Harbaugh is known as the daughter of longtime Baltimore Ravens head coach John Harbaugh.
-
E.
Ingrid Harbaugh
Ingrid Harbaugh is the wife of longtime Baltimore Ravens head coach John Harbaugh and is known for her involvement in charitable and community activities connected to the team.
- 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_69b34553cbe48190afa8ac1cac285b86 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b356dddd488190bd5dedd3c0e77247 |
completed | March 13, 2026, 12:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b6377c694881909428b5cffb405c8d |
completed | March 15, 2026, 4:37 a.m. |
| NEDg | Description generation | batch_69b6384b32c08190969a892ccc135b2f |
completed | March 15, 2026, 4:40 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b63c3585b08190ab6837ffdb6db73e |
completed | March 15, 2026, 4:57 a.m. |
Created at: March 12, 2026, 11:36 p.m.