Triple
T23771185
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eurovision Song Contest 2007 |
E587529
|
entity |
| Predicate | runnerUpPerformer |
P2683
|
FINISHED |
| Object | Verka Serduchka |
—
|
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: Verka Serduchka | Statement: [Eurovision Song Contest 2007, runnerUpPerformer, Verka Serduchka]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: runnerUpPerformer Context triple: [Eurovision Song Contest 2007, runnerUpPerformer, Verka Serduchka]
-
A.
runnerUp
chosen
Indicates that one entity finished in second place relative to another in a competition or ranking.
-
B.
runnerUpRank
Indicates the position or ranking assigned to an entity that finishes immediately after the winner (or near the top) in a competition or ordered list.
-
C.
runnerUpWins
Indicates that an entity finishes in second place in a competition or ranking and receives the corresponding runner-up victory or award.
-
D.
runnerUpCountry
Indicates the country that finished in second place in a competition or ranking.
-
E.
runnerUpManager
Indicates that one entity serves as the manager or coach of another entity who finished as the runner-up in a competition or ranking.
- 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_69e2490d245881909028226a1393d624 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1c466d21c8190b45aa7a1d61a83be |
completed | April 29, 2026, 8:42 a.m. |
| PD | Predicate disambiguation | batch_69f155f79e34819080f9ddb972b34deb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:15 p.m.