Triple
T31996501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Unexpected |
E817005
|
entity |
| Predicate | collectedEditionFormat |
P102437
|
FINISHED |
| Object | trade paperback |
—
|
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: trade paperback | Statement: [The Unexpected, collectedEditionFormat, trade paperback]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collectedEditionFormat Context triple: [The Unexpected, collectedEditionFormat, trade paperback]
-
A.
hasCollectedEdition
Indicates that one entity possesses or maintains a special or curated edition or version of another entity as part of a collection.
-
B.
pageCountOfCollectedEdition
Indicates the total number of pages contained in a collected or compiled edition of a work.
-
C.
presentedInFormat
chosen
Indicates that something is expressed, delivered, or made available using a particular format or representation.
-
D.
circulationFormat
Indicates the medium or format in which an item is made available for circulation or lending (e.g., physical, digital, audio).
-
E.
republicationFormat
Indicates the format or medium in which something is republished, such as a new edition, platform, or presentation type.
- F. None of above.
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_69f348f8002081909a3588758ba94afb |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fbc9d1dba881908c399b8e1dc13ce2 |
completed | May 6, 2026, 11:08 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ec03ac8190a757563f96fab283 |
completed | May 6, 2026, 11:04 p.m. |
Created at: May 1, 2026, 12:13 a.m.