Triple
T10966562
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harding |
E259114
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object |
Paul Harding
Paul Harding is an American novelist best known for his Pulitzer Prize–winning debut novel "Tinkers."
|
E897359
|
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: Paul Harding | Statement: [Harding, hasNotableBearer, Paul Harding]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Harding Context triple: [Harding, hasNotableBearer, Paul Harding]
-
A.
Adam Haslett
Adam Haslett is an American author and journalist known for his critically acclaimed fiction exploring themes of mental illness, family, and contemporary politics.
-
B.
Adam Johnson
Adam Johnson is a Pulitzer Prize–winning American author best known for his novel "The Orphan Master's Son," which explores life in North Korea.
-
C.
Greg Grabianski
Greg Grabianski is a screenwriter best known for his work on the parody horror-comedy film "Scary Movie 2."
-
D.
T.C. Boyle
T.C. Boyle is an American novelist and short story writer known for his darkly comic, stylistically inventive fiction and exploration of social and environmental themes.
-
E.
Stewart O'Nan
Stewart O'Nan is an American novelist known for his quietly powerful, character-driven fiction that often explores the lives of ordinary people in contemporary America.
- 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: Paul Harding Triple: [Harding, hasNotableBearer, Paul Harding]
Generated description
Paul Harding is an American novelist best known for his Pulitzer Prize–winning debut novel "Tinkers."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Paul Harding Target entity description: Paul Harding is an American novelist best known for his Pulitzer Prize–winning debut novel "Tinkers."
-
A.
Adam Haslett
Adam Haslett is an American author and journalist known for his critically acclaimed fiction exploring themes of mental illness, family, and contemporary politics.
-
B.
Adam Johnson
Adam Johnson is a Pulitzer Prize–winning American author best known for his novel "The Orphan Master's Son," which explores life in North Korea.
-
C.
Greg Grabianski
Greg Grabianski is a screenwriter best known for his work on the parody horror-comedy film "Scary Movie 2."
-
D.
T.C. Boyle
T.C. Boyle is an American novelist and short story writer known for his darkly comic, stylistically inventive fiction and exploration of social and environmental themes.
-
E.
Stewart O'Nan
Stewart O'Nan is an American novelist known for his quietly powerful, character-driven fiction that often explores the lives of ordinary people in contemporary America.
- 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_69d6aa88500c819097d7032ca578e74f |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d77149c0448190a66322fa696fdbda |
completed | April 9, 2026, 9:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e2d78156c48190a956dc22b9832bcb |
completed | April 18, 2026, 12:59 a.m. |
| NEDg | Description generation | batch_69e2ff1ffb8c8190ba97f3c2e3c8c601 |
completed | April 18, 2026, 3:48 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69e3261cc4f48190ba0e5645f37cd4b5 |
completed | April 18, 2026, 6:35 a.m. |
Created at: April 8, 2026, 9:24 p.m.