Triple
T23509412
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Red Rum |
E572374
|
entity |
| Predicate | finishedSecondIn |
P129552
|
FINISHED |
| Object | 1975 Grand National |
—
|
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: 1975 Grand National | Statement: [Red Rum, finishedSecondIn, 1975 Grand National]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: finishedSecondIn Context triple: [Red Rum, finishedSecondIn, 1975 Grand National]
-
A.
finishedSecondInRace
chosen
Indicates that an entity completed a race in second place relative to other competitors.
-
B.
finishedAheadOf
Indicates that one entity completed an event, task, or process before another entity, ranking or finishing in a superior or earlier position.
-
C.
finishSetting
Indicates that an entity completes configuring or establishing a particular setting or set of settings for another entity or context.
-
D.
finishedRecord
Indicates that an entity has completed or finalized the creation, processing, or updating of a record.
-
E.
completedAfter
Indicates that one event or task was finished at a later time than another specified event or task.
- 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_69e245b5e4208190bac8a6509867e394 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a902c0788190840d7df1b5450b4d |
completed | April 29, 2026, 6:45 a.m. |
| PD | Predicate disambiguation | batch_69f0621165c08190a0b27b1319733959 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 6:07 p.m.