Triple
T123645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvard University Press |
E2498
|
entity |
| Predicate | hasPublishingFormat |
P5128
|
FINISHED |
| Object | print books |
—
|
LITERAL 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: print books | Statement: [Harvard University Press, hasPublishingFormat, print books]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPublishingFormat Context triple: [Harvard University Press, hasPublishingFormat, print books]
-
A.
hasPublisher
Indicates that an entity is published or issued by a specific publisher.
-
B.
hasPublication
Indicates that an entity is associated with or responsible for a specific publication.
-
C.
publishingModel
Indicates the method or framework by which content is produced, distributed, and made publicly available.
-
D.
hasSisterPublication
Indicates that one publication is related to another as a sister publication, typically under the same parent organization or closely associated in scope or branding.
-
E.
publishedFor
Indicates that something (such as a work, document, or content) is published with a particular audience, recipient, or target group in mind.
- F. None of above. chosen
Provenance (4 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_69a251b54ea88190b18281669f59b4c0 |
completed | Feb. 28, 2026, 2:23 a.m. |
| NER | Named-entity recognition | batch_69a2573ce0ac8190b49fb31d3d475bf9 |
completed | Feb. 28, 2026, 2:47 a.m. |
| PD | Predicate disambiguation | batch_69a2564928208190966a619680a0d6e2 |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a256c72f6c81909b619b90d829d86e |
completed | Feb. 28, 2026, 2:45 a.m. |
Created at: Feb. 28, 2026, 2:27 a.m.