Triple
T27762548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Susan Hill |
E701504
|
entity |
| Predicate | SomersetMaughamAwardFor |
P163226
|
FINISHED |
| Object | I'm the King of the Castle |
—
|
NE NERFINISHED |
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: I'm the King of the Castle | Statement: [Susan Hill, SomersetMaughamAwardFor, I'm the King of the Castle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: SomersetMaughamAwardFor Context triple: [Susan Hill, SomersetMaughamAwardFor, I'm the King of the Castle]
-
A.
novelAward
Indicates that an entity has received an award specifically for a novel.
-
B.
sharesBookerPrizeWith
Indicates that two entities have both received the Booker Prize, sharing this literary award in common.
-
C.
Libris Literatuur Prijs
Indicates the relationship of a work or author being the recipient or subject of the Libris Literatuur Prijs literary award.
-
D.
dateAwarded Pulitzer Prize for Fiction
Indicates that a specific date is when an entity received the Pulitzer Prize for Fiction.
-
E.
awardWithinFiction
Indicates that an award is given or exists within a fictional context or narrative world, rather than in real life.
- 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_69ef6a5193808190816eb7d0020b2d87 |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f63766dcc48190a916106fbf8ad619 |
completed | May 2, 2026, 5:41 p.m. |
| PD | Predicate disambiguation | batch_69f63188e7408190af8ce8b93d128c63 |
completed | May 2, 2026, 5:16 p.m. |
| PDg | Predicate description generation | batch_69f6352df6148190bc10772cd40bd7b3 |
completed | May 2, 2026, 5:32 p.m. |
Created at: April 27, 2026, 4:28 p.m.