Triple
T9783630
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kentucky Three-Day Event |
E237437
|
entity |
| Predicate | day2Phase |
P8970
|
FINISHED |
| Object | dressage |
—
|
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: dressage | Statement: [Kentucky Three-Day Event, day2Phase, dressage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: day2Phase Context triple: [Kentucky Three-Day Event, day2Phase, dressage]
-
A.
day8Form
Indicates a relationship where an entity is associated with a specific form, version, or configuration that is designated as "day 8" in a sequence or schedule.
-
B.
secondPhase
chosen
Indicates that an entity is in, or has progressed to, the second phase or stage of a multi-phase process or sequence.
-
C.
phase2Purpose
Indicates the specific intended goal, function, or outcome associated with the second phase of a process or project.
-
D.
phase
Indicates that one entity is in a particular stage, step, or phase within a process, sequence, or lifecycle relative to another reference.
-
E.
day3Form
Indicates a form or document that is specifically associated with, or must be completed by, the third day of a given process or timeline.
- 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_69ca84da927881909bda80caecad6010 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda1b7740c8190bfb4997eb683d78a |
completed | April 1, 2026, 10:52 p.m. |
| PD | Predicate disambiguation | batch_69cd03d77c6c81909b675955bf113320 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:27 p.m.