Triple
T1543233
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herb Kelleher |
E32916
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Jo Ann Kelleher
Jo Ann Kelleher is best known as the wife of Herb Kelleher, the co-founder and longtime CEO of Southwest Airlines.
|
E246388
|
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: Jo Ann Kelleher | Statement: [Herb Kelleher, spouse, Jo Ann Kelleher]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jo Ann Kelleher Context triple: [Herb Kelleher, spouse, Jo Ann Kelleher]
-
A.
Nancy Shevell
Nancy Shevell is an American businesswoman and heiress best known for her long-term relationship and marriage to musician Paul McCartney.
-
B.
Mary Ellen Trainor
Mary Ellen Trainor was an American actress known for her supporting roles in popular 1980s and 1990s films such as "The Goonies," "Lethal Weapon," and "Die Hard."
-
C.
Diane Bemus Patrick
Diane Bemus Patrick is an American attorney and mental health advocate best known as the wife of former Massachusetts governor Deval Patrick.
-
D.
Kathleen Buchanan Smith
Kathleen Buchanan Smith was the wife of British physicist and Nobel laureate George Paget Thomson.
-
E.
Linda Pizzuti Henry
Linda Pizzuti Henry is an American businesswoman and media executive, known for her leadership role at The Boston Globe and involvement in Fenway Sports Group.
- 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: Jo Ann Kelleher Triple: [Herb Kelleher, spouse, Jo Ann Kelleher]
Generated description
Jo Ann Kelleher is best known as the wife of Herb Kelleher, the co-founder and longtime CEO of Southwest Airlines.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Jo Ann Kelleher Target entity description: Jo Ann Kelleher is best known as the wife of Herb Kelleher, the co-founder and longtime CEO of Southwest Airlines.
-
A.
Nancy Shevell
Nancy Shevell is an American businesswoman and heiress best known for her long-term relationship and marriage to musician Paul McCartney.
-
B.
Mary Ellen Trainor
Mary Ellen Trainor was an American actress known for her supporting roles in popular 1980s and 1990s films such as "The Goonies," "Lethal Weapon," and "Die Hard."
-
C.
Diane Bemus Patrick
Diane Bemus Patrick is an American attorney and mental health advocate best known as the wife of former Massachusetts governor Deval Patrick.
-
D.
Kathleen Buchanan Smith
Kathleen Buchanan Smith was the wife of British physicist and Nobel laureate George Paget Thomson.
-
E.
Linda Pizzuti Henry
Linda Pizzuti Henry is an American businesswoman and media executive, known for her leadership role at The Boston Globe and involvement in Fenway Sports Group.
- 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_69a885ed29088190a3c2d5a3d100c16e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a9084140f0819098c81d295d08d480 |
completed | March 5, 2026, 4:36 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae6adcef5881908cefd7d575b85323 |
completed | March 9, 2026, 6:38 a.m. |
| NEDg | Description generation | batch_69ae6b31eccc81908fbcc80f72e65df8 |
completed | March 9, 2026, 6:39 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae6bd2856c81909033efe74039c258 |
completed | March 9, 2026, 6:42 a.m. |
Created at: March 4, 2026, 7:26 p.m.