Triple
T17921153
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Carney |
E448068
|
entity |
| Predicate | workedWith |
P398
|
FINISHED |
| Object | Markéta Irglová |
—
|
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: Markéta Irglová | Statement: [John Carney, workedWith, Markéta Irglová]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Markéta Irglová Context triple: [John Carney, workedWith, Markéta Irglová]
-
A.
Markéta Irglová
chosen
Markéta Irglová is a Czech singer-songwriter, pianist, and actress best known for co-starring in the film "Once" and winning the Academy Award for Best Original Song for "Falling Slowly."
-
B.
Markéta Vaňková
Markéta Vaňková is a Czech politician who serves as the mayor of Brno, one of the country’s largest cities.
-
C.
Tatiana Vilhelmová
Tatiana Vilhelmová is a Czech film and theatre actress known for her acclaimed performances in contemporary Czech cinema and stage productions.
-
D.
Veronika Jenet
Veronika Jenet is an Australian film editor best known for her acclaimed work on feature films such as "The Piano."
-
E.
Rita Vrataski
Rita Vrataski is a legendary, battle-hardened soldier known as the "Full Metal Bitch" in the military science fiction story "All You Need Is Kill," where she mentors the protagonist in humanity’s war against alien invaders.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f6d394819082a6d69fd1e23d2f |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4a30a11748190be41361d108aee58 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 10:20 a.m.