Triple
T4240513
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Theodore Samuel Williams |
E95399
|
entity |
| Predicate | TripleCrownYear |
P7542
|
FINISHED |
| Object | 1942 |
—
|
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: 1942 | Statement: [Theodore Samuel Williams, TripleCrownYear, 1942]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: TripleCrownYear Context triple: [Theodore Samuel Williams, TripleCrownYear, 1942]
-
A.
tripleCrownYear
chosen
Indicates the year in which an entity achieved a Triple Crown title or completed a Triple Crown accomplishment.
-
B.
previousTripleCrownYear
Indicates that the subject year is the most recent year before the object year in which a Triple Crown (e.g., in horse racing) was achieved.
-
C.
tripleCrownWinner
Indicates that an entity has won all three major titles or championships that together constitute a "Triple Crown" within a particular sport or competitive domain.
-
D.
previousTripleCrownWinner
Indicates that one entity is the Triple Crown winner who immediately preceded the other entity in time.
-
E.
tripleCrownStatus
Indicates whether an entity has achieved, is pursuing, or holds a specific standing related to a recognized "triple crown" set of three major accomplishments or titles.
- 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_69b3453d91548190b4d4ef8fe52aa2ac |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34e77fb5c8190b298818acb68ff63 |
completed | March 12, 2026, 11:38 p.m. |
| PD | Predicate disambiguation | batch_69b347f587148190a1830503459939b6 |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:05 p.m.