Triple
T9620513
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Penguin General |
E232329
|
entity |
| Predicate | overseesImprint |
P89294
|
FINISHED |
| Object | Fig Tree |
—
|
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: Fig Tree | Statement: [Penguin General, overseesImprint, Fig Tree]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: overseesImprint Context triple: [Penguin General, overseesImprint, Fig Tree]
-
A.
imprintsOn
Indicates that one entity forms a strong, often instinctive or formative attachment or bond to another, typically as a primary reference or guide.
-
B.
publisherImprint
Indicates the publishing imprint or brand under which a work is issued by a publisher.
-
C.
hadImprint
Indicates that one entity bears or once bore a physical or symbolic mark, stamp, or impression produced by another entity.
-
D.
imprintedOn
Indicates that one entity has formed a strong, often early-life, attachment or bond to another entity, typically treating it as a primary reference or caregiver.
-
E.
hasParentImprint
Indicates that one publishing imprint is the parent or controlling imprint of another imprint.
- 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_69ca84867bb88190b4b57dd5a56d5691 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9ad3a8d88190b1414aa676d82f36 |
completed | April 1, 2026, 10:23 p.m. |
| PD | Predicate disambiguation | batch_69ccd5aa1d2c8190a287bf1cf4a3037e |
completed | April 1, 2026, 8:22 a.m. |
| PDg | Predicate description generation | batch_69ccd93fc45c8190a823305e461e581d |
completed | April 1, 2026, 8:37 a.m. |
Created at: March 30, 2026, 8:09 p.m.