Triple
T17919784
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kathleen Burke |
E448034
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Lyle Lahey
Lyle Lahey was an American editorial cartoonist known for his long-running political cartoons in Wisconsin newspapers.
|
E1327227
|
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: Lyle Lahey | Statement: [Kathleen Burke, spouse, Lyle Lahey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lyle Lahey Context triple: [Kathleen Burke, spouse, Lyle Lahey]
-
A.
Lyle Workman
Lyle Workman is an American guitarist and film composer known for his work on numerous comedy soundtracks and collaborations with artists like Beck and Todd Rundgren.
-
B.
Lyle Boyer
Lyle Boyer is an editor known for his work on the film "Bedlam."
-
C.
Lyle Anderson
Lyle Anderson is a fictional character appearing in the "Kingdom" series.
-
D.
Patrick Lahey
Patrick Lahey is a deep-sea explorer and submersible designer best known as the co-founder and president of Triton Submarines and for piloting record-setting dives to the ocean’s deepest points.
-
E.
George LaVoo
George LaVoo is an American filmmaker and screenwriter best known for his work on independent films, including the acclaimed coming-of-age drama "Real Women Have Curves."
- 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: Lyle Lahey Triple: [Kathleen Burke, spouse, Lyle Lahey]
Generated description
Lyle Lahey was an American editorial cartoonist known for his long-running political cartoons in Wisconsin newspapers.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lyle Lahey Target entity description: Lyle Lahey was an American editorial cartoonist known for his long-running political cartoons in Wisconsin newspapers.
-
A.
Lyle Workman
Lyle Workman is an American guitarist and film composer known for his work on numerous comedy soundtracks and collaborations with artists like Beck and Todd Rundgren.
-
B.
Lyle Boyer
Lyle Boyer is an editor known for his work on the film "Bedlam."
-
C.
Lyle Anderson
Lyle Anderson is a fictional character appearing in the "Kingdom" series.
-
D.
Patrick Lahey
Patrick Lahey is a deep-sea explorer and submersible designer best known as the co-founder and president of Triton Submarines and for piloting record-setting dives to the ocean’s deepest points.
-
E.
George LaVoo
George LaVoo is an American filmmaker and screenwriter best known for his work on independent films, including the acclaimed coming-of-age drama "Real Women Have Curves."
- 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_69d8b9f6d394819082a6d69fd1e23d2f |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4a309532881908633bd723923880f |
completed | April 19, 2026, 9:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a047125683081908a18067ff3fd7956 |
completed | May 13, 2026, 12:40 p.m. |
| NEDg | Description generation | batch_6a04730c241c8190800aa4c99dfa5c08 |
completed | May 13, 2026, 12:48 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0473c5c03c8190956a5d640cfd579d |
completed | May 13, 2026, 12:51 p.m. |
Created at: April 10, 2026, 10:20 a.m.