Triple
T7714611
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Goodbye Bafana |
E174849
|
entity |
| Predicate | basedOnAuthor |
P2806
|
FINISHED |
| Object |
Bob Graham
Bob Graham is an Australian author and illustrator best known for his award-winning children's picture books.
|
E685410
|
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: Bob Graham | Statement: [Goodbye Bafana, basedOnAuthor, Bob Graham]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bob Graham Context triple: [Goodbye Bafana, basedOnAuthor, Bob Graham]
-
A.
Jim Wright
Jim Wright was an American Democratic politician from Texas who served as a powerful congressional leader and later Speaker of the U.S. House of Representatives in the 1980s.
-
B.
Howard E. Smith
Howard E. Smith is a film editor best known for his work on the acclaimed drama "Glengarry Glen Ross."
-
C.
Howard E. Smith
Howard E. Smith is a film editor best known for his work on the thriller "Snakes on a Plane."
-
D.
Howard A. Smith
Howard A. Smith was a film editor best known for his work on classic Hollywood movies, including the 1961 romantic comedy "Breakfast at Tiffany's."
-
E.
Howard W. Smith
Howard W. Smith was a powerful mid-20th-century Virginia congressman and conservative Democrat known for his influential role on the House Rules Committee and his opposition to New Deal and civil rights legislation.
- 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: Bob Graham Triple: [Goodbye Bafana, basedOnAuthor, Bob Graham]
Generated description
Bob Graham is an Australian author and illustrator best known for his award-winning children's picture books.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bob Graham Target entity description: Bob Graham is an Australian author and illustrator best known for his award-winning children's picture books.
-
A.
Jim Wright
Jim Wright was an American Democratic politician from Texas who served as a powerful congressional leader and later Speaker of the U.S. House of Representatives in the 1980s.
-
B.
Howard E. Smith
Howard E. Smith is a film editor best known for his work on the acclaimed drama "Glengarry Glen Ross."
-
C.
Howard E. Smith
Howard E. Smith is a film editor best known for his work on the thriller "Snakes on a Plane."
-
D.
Howard A. Smith
Howard A. Smith was a film editor best known for his work on classic Hollywood movies, including the 1961 romantic comedy "Breakfast at Tiffany's."
-
E.
Howard W. Smith
Howard W. Smith was a powerful mid-20th-century Virginia congressman and conservative Democrat known for his influential role on the House Rules Committee and his opposition to New Deal and civil rights legislation.
- 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_69c6995c463c8190a14458036249d419 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c702ca8f048190a6ea27b8cee2f93e |
completed | March 27, 2026, 10:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8be2831788190a8ba7340b5d4d439 |
completed | March 29, 2026, 5:52 a.m. |
| NEDg | Description generation | batch_69c8bee8adf4819093dd468266f0e65c |
completed | March 29, 2026, 5:55 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c8bf7db7888190bbb4dede2f0dbf53 |
completed | March 29, 2026, 5:58 a.m. |
Created at: March 27, 2026, 4:04 p.m.