Triple
T18318568
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Masar |
E438809
|
entity |
| Predicate | raceDate |
P47077
|
FINISHED |
| Object | won the 2018 Epsom Derby on 2 June 2018 |
—
|
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: won the 2018 Epsom Derby on 2 June 2018 | Statement: [Masar, raceDate, won the 2018 Epsom Derby on 2 June 2018]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: raceDate Context triple: [Masar, raceDate, won the 2018 Epsom Derby on 2 June 2018]
-
A.
raceDayIncludes
Indicates that a particular race day schedule or event set contains or encompasses a specific race or racing-related activity.
-
B.
raceMeeting
Indicates a competitive event where multiple participants race against each other under shared rules and conditions.
-
C.
raceRecord
Indicates that there exists a recorded result or performance entry for an entity participating in a race or competitive event.
-
D.
raceTrack
Indicates that one entity serves as a race track or racing course used by another entity for racing activities.
-
E.
timingOfRace
chosen
Indicates the temporal details or schedule associated with a race, such as its start time, duration, or overall timing.
- 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_69d8b916a2d081909e249e4902f6aad9 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50aa342a881909afcd995405027af |
completed | April 19, 2026, 5:02 p.m. |
| PD | Predicate disambiguation | batch_69e44fe4ee10819086b4142444fca1f5 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:36 a.m.