Triple
T945899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jaws (novel) |
E20412
|
entity |
| Predicate | publisher |
P29
|
FINISHED |
| Object | Doubleday |
E22938
|
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: Doubleday | Statement: [Jaws (novel), publisher, Doubleday]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Doubleday Context triple: [Jaws (novel), publisher, Doubleday]
-
A.
Doubleday
chosen
Doubleday is a major American publishing company known for releasing a wide range of influential fiction and nonfiction books.
-
B.
Random House
Random House is a major American book publishing company known for releasing a wide range of influential fiction and nonfiction titles.
-
C.
Alfred A. Knopf
Alfred A. Knopf is a prestigious American publishing house known for its high-quality literary fiction and nonfiction titles.
-
D.
Simon & Schuster
Simon & Schuster is a major American publishing company known for producing a wide range of bestselling fiction and nonfiction books.
-
E.
Harper & Row
Harper & Row was a major American publishing house known for producing influential works in literature, education, and academic scholarship.
- 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_69a493b0f2fc81908cd227480a5356a1 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b3a61b648190b1b6c932e047e161 |
completed | March 1, 2026, 9:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acc5ff51c48190ab9b096d9d885d8f |
completed | March 8, 2026, 12:42 a.m. |
Created at: March 1, 2026, 7:40 p.m.