Triple
T21856002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hambletonian Stakes |
E539627
|
entity |
| Predicate | eligibleAge |
P14567
|
FINISHED |
| Object | three-year-old |
—
|
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: three-year-old | Statement: [Hambletonian Stakes, eligibleAge, three-year-old]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eligibleAge Context triple: [Hambletonian Stakes, eligibleAge, three-year-old]
-
A.
canAgeFor
Indicates that one entity is capable of undergoing an aging or maturation process for the benefit, use, or context of another entity.
-
B.
typicalEligibilityAge
chosen
Indicates the usual or standard age at which an entity qualifies for or becomes eligible for a particular status, benefit, or activity.
-
C.
containsAge
Indicates that one entity includes or specifies the age value or age-related information of another entity.
-
D.
ageConstraint
Indicates a restriction or condition based on the age of an entity relative to a specified threshold or range.
-
E.
ageStatus
Indicates the relationship between an entity and its classification into an age-related category or status (e.g., minor, adult, senior).
- 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_69e0c47829648190bbe2d1d7033768ec |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0d635b59c81908810480f3802b847 |
completed | April 28, 2026, 3:45 p.m. |
| PD | Predicate disambiguation | batch_69e6be9394f88190945ddd1dc004d29d |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 6:56 p.m.