Triple
T30094124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King George Weekend |
E764815
|
entity |
| Predicate | highlightEvent |
P65072
|
FINISHED |
| Object | King George VI and Queen Elizabeth Stakes |
—
|
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: King George VI and Queen Elizabeth Stakes | Statement: [King George Weekend, highlightEvent, King George VI and Queen Elizabeth Stakes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: highlightEvent Context triple: [King George Weekend, highlightEvent, King George VI and Queen Elizabeth Stakes]
-
A.
highlightsSign
Indicates that one entity visually emphasizes or draws special attention to a sign.
-
B.
recordHighlight
Indicates that an entity is marked or stored as a notable or emphasized point within a larger record or sequence.
-
C.
isMajorHighlightOf
chosen
Indicates that something serves as a primary or especially notable feature, event, or focal point within a larger context or whole.
-
D.
peakEvent
Indicates the occurrence of a maximum or most intense point within a process, activity, or measurable phenomenon.
-
E.
highlights
Indicates that one entity draws special attention to, emphasizes, or visually marks another entity as important or noteworthy.
- 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_69f22474e4288190b5f895fe3974aa92 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67d8e989081909d062bcf86c82ca2 |
completed | May 2, 2026, 10:41 p.m. |
| PD | Predicate disambiguation | batch_69f673c664f08190b4d66cdc305e10db |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:06 p.m.