Triple
T30288500
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Costa Book Award for Best Novel (shortlisted) |
E770303
|
entity |
| Predicate | previousNamePeriodEnd |
P17450
|
FINISHED |
| Object | 2005 |
—
|
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: 2005 | Statement: [Costa Book Award for Best Novel (shortlisted), previousNamePeriodEnd, 2005]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousNamePeriodEnd Context triple: [Costa Book Award for Best Novel (shortlisted), previousNamePeriodEnd, 2005]
-
A.
formerNamePeriodEnd
chosen
Indicates the point in time when an entity stopped using a former name.
-
B.
previousNamePeriod
Indicates the time span during which an entity was known by a former name before changing to its current name.
-
C.
previousNameUsedUntil
Indicates that a particular name was used for an entity up to (but not necessarily including) a specified end date or time.
-
D.
formerNamePeriodStart
Indicates the date or time point when an entity began using a former name that is being recorded.
-
E.
previousNameOfDate
Indicates that one date was formerly known or designated by another date, representing a prior naming or labeling of the same temporal reference.
- 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_69f224875c288190a9b96b975006ec4a |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fdd07a34c08190982b8c61c2775cf6 |
completed | May 8, 2026, noon |
| PD | Predicate disambiguation | batch_69fdbd25c7908190b72fca8de7ce503f |
completed | May 8, 2026, 10:38 a.m. |
Created at: April 29, 2026, 7:46 p.m.