Triple
T8280351
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Forrest Church |
E193654
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
Frank
Frank is the first name of Forrest Church, an American Unitarian Universalist minister, theologian, and author.
|
E723254
|
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: Frank | Statement: [Forrest Church, givenName, Frank]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frank Context triple: [Forrest Church, givenName, Frank]
-
A.
Frank
Frank is a key supporting character in the post-apocalyptic horror film "28 Days Later," known as a protective father trying to keep his daughter safe amid a devastating viral outbreak in London.
-
B.
Frank
Frank is the given name of Frank Abagnale Jr., the infamous former con artist whose life inspired the film "Catch Me If You Can."
-
C.
Frank
Frank is the given name of British screenwriter and children's author Frank Cottrell-Boyce.
-
D.
Frank
Frank is the given name of British former professional heavyweight boxer Frank Bruno, a popular sports figure especially known in the UK.
-
E.
Frank
Frank is an alternate given name of longtime Republican U.S. Congressman Jim Sensenbrenner, who represented a Wisconsin district in the House of Representatives for four decades.
- 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: Frank Triple: [Forrest Church, givenName, Frank]
Generated description
Frank is the first name of Forrest Church, an American Unitarian Universalist minister, theologian, and author.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Frank Target entity description: Frank is the first name of Forrest Church, an American Unitarian Universalist minister, theologian, and author.
-
A.
Frank
Frank is the given name of Frank McCourt, the Irish-American teacher and Pulitzer Prize–winning author best known for his memoir "Angela’s Ashes."
-
B.
Frank
Frank is the given name of Frank B. Kellogg, an American lawyer, diplomat, and Nobel Peace Prize–winning U.S. Secretary of State.
-
C.
Frank
Frank is the given name of the British philosopher, mathematician, and economist F. P. Ramsey, known for his influential work in logic, probability, and the foundations of mathematics.
-
D.
Frank
Frank is the given first name of the American contemporary street artist and graphic designer Shepard Fairey, known for his iconic "OBEY" and Barack Obama "Hope" posters.
-
E.
Frank
Frank is the given name of the American painter, sculptor, and printmaker Frank Stella, a leading figure in minimalism and post-painterly abstraction.
- 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_69ca82e217a48190880695635c44b2ed |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb79ee66e48190af7058b14f3daac9 |
completed | March 31, 2026, 7:38 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd686d9be081908b0490e708f51ad7 |
completed | April 1, 2026, 6:48 p.m. |
| NEDg | Description generation | batch_69cd6d5441248190a9e32281dc8e8d62 |
completed | April 1, 2026, 7:09 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cd7e20f71c8190959319c6683a2810 |
completed | April 1, 2026, 8:20 p.m. |
Created at: March 30, 2026, 5:51 p.m.