Triple
T5501495
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hit Refresh |
E144338
|
entity |
| Predicate | publisher |
P29
|
FINISHED |
| Object | Harper Business |
E65842
|
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: Harper Business | Statement: [Hit Refresh, publisher, Harper Business]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harper Business Context triple: [Hit Refresh, publisher, Harper Business]
-
A.
HarperCollins
chosen
HarperCollins is a major global publishing company known for producing a wide range of fiction, non-fiction, and educational 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.
Harper Perennial
Harper Perennial is an imprint of HarperCollins known for publishing contemporary literary fiction, nonfiction, and reissues of classic works in affordable paperback editions.
-
D.
Harper & Row
Harper & Row was a major American publishing house known for producing influential works in literature, education, and academic scholarship.
-
E.
Penguin Random House
Penguin Random House is a major global trade book publisher known for its extensive catalog of fiction and nonfiction titles across numerous imprints.
- 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_69c008f5a2748190bce7a39aabf87a6d |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c01f0a512c81908f077378917e5879 |
completed | March 22, 2026, 4:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c027a10fa08190853d45354fd9b044 |
completed | March 22, 2026, 5:32 p.m. |
Created at: March 22, 2026, 3:32 p.m.