Triple
T7357130
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Holes |
E169653
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Louis Sachar |
E658807
|
NE FINISHED |
How this triple was built (2 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: Louis Sachar | Statement: [Holes, screenwriter, Louis Sachar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Louis Sachar Context triple: [Holes, screenwriter, Louis Sachar]
-
A.
Louis Sachar
chosen
Louis Sachar is an American children's author best known for his novel "Holes," as well as the "Wayside School" series.
-
B.
Edith Sachar
Edith Sachar was an American sculptor and jewelry designer active in the mid-20th century, known for her modernist metalwork and association with the New York art scene.
-
C.
James Howe Jr.
James Howe Jr. was a 17th-century New England colonist known primarily as the husband of Elizabeth Howe, one of the women executed during the Salem witch trials.
-
D.
Chris Riddell
Chris Riddell is a British illustrator and political cartoonist renowned for his distinctive artwork in children's literature and fantasy novels.
-
E.
David Ebershoff
David Ebershoff is an American author and editor best known for his novel "The Danish Girl," which was adapted into an acclaimed feature film.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69c68a59f2288190877ca15c19b1e822 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f13a62e48190a2d1781a630aa9f0 |
completed | March 27, 2026, 9:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c802b69cb4819096815b1fac284840 |
completed | March 28, 2026, 4:32 p.m. |
Created at: March 27, 2026, 3:06 p.m.