Triple
T23802172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tomas Berdych |
E588701
|
entity |
| Predicate | usOpenBestResult |
P153609
|
FINISHED |
| Object | semifinalist |
—
|
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: semifinalist | Statement: [Tomas Berdych, usOpenBestResult, semifinalist]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usOpenBestResult Context triple: [Tomas Berdych, usOpenBestResult, semifinalist]
-
A.
bestF1Result
Indicates that one result in a set has the highest F1 score (harmonic mean of precision and recall) compared to all other results.
-
B.
usOpenWinsCount
Indicates the number of times an entity has won the US Open tournament.
-
C.
bestOnBest
Indicates that the relationship or action occurs under conditions where each side is using its strongest or highest-performing option against the other's strongest or highest-performing option.
-
D.
bestResultsCounted
Indicates that the number of best or top-performing results in a given context has been determined and recorded.
-
E.
bestForward
Indicates that the subject is considered the most effective or outstanding forward (e.g., in an offensive or attacking role) relative to a given group or context.
- F. None of above. chosen
Provenance (4 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_69e25d15db58819092ac1e6791696fd9 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c74e430481909debd10c71785912 |
completed | April 29, 2026, 8:54 a.m. |
| PD | Predicate disambiguation | batch_69f155fe300481909bd617443228df65 |
completed | April 29, 2026, 12:51 a.m. |
| PDg | Predicate description generation | batch_69f15adb23d88190ac2632299c26a9b3 |
completed | April 29, 2026, 1:11 a.m. |
Created at: April 17, 2026, 7:53 p.m.