Triple
T34174070
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1927 Schneider Trophy |
E876618
|
entity |
| Predicate | thirdPlacePilot |
P35718
|
FINISHED |
| Object | Mario de Bernardi |
—
|
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: Mario de Bernardi | Statement: [1927 Schneider Trophy, thirdPlacePilot, Mario de Bernardi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: thirdPlacePilot Context triple: [1927 Schneider Trophy, thirdPlacePilot, Mario de Bernardi]
-
A.
thirdPlaceCandidate
chosen
Indicates that the subject is the candidate who finished in third place in a competition, ranking, or election.
-
B.
thirdPlaceRank
Indicates that an entity holds the third position in a ranking or ordered list relative to others.
-
C.
thirdPlacePrize
Indicates that an entity receives or is associated with the prize awarded for finishing in third place in a competition or ranking.
-
D.
thirdEpisode
Indicates that one entity is the third episode in sequence within a series or season relative to another entity.
-
E.
thirdElement
Indicates that one entity is the third element in an ordered sequence or tuple associated with another entity.
- 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_69f349ad97ac8190bf1f17417c970e64 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69fcc7338120819081cb46547d60f2cb |
completed | May 7, 2026, 5:09 p.m. |
| PD | Predicate disambiguation | batch_69fcc58566a0819082d5ea36e03bf0c6 |
completed | May 7, 2026, 5:01 p.m. |
Created at: May 1, 2026, 1:54 a.m.