Triple
T22336238
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ana Ivanovic |
E552153
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Ivanovic |
—
|
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: Ivanovic | Statement: [Ana Ivanovic, familyName, Ivanovic]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ivanovic Context triple: [Ana Ivanovic, familyName, Ivanovic]
-
A.
Ana Ivanovic
chosen
Ana Ivanovic is a retired Serbian professional tennis player and former world No. 1 who won the 2008 French Open singles title.
-
B.
Bojana Jankovic
Bojana Jankovic is a Serbian-born physician and wellness expert best known as the wife of American actor Michael Weatherly.
-
C.
Jelena Djokovic
Jelena Djokovic is a Serbian humanitarian and businesswoman, best known as the wife of tennis champion Novak Djokovic and the co-founder and director of the Novak Djokovic Foundation.
-
D.
Janković
Janković is a South Slavic surname, common in Serbian and neighboring cultures, borne by various notable figures in sports, politics, and the arts.
-
E.
Andrea Petkovic
Andrea Petkovic is a retired German professional tennis player known for her powerful baseline game, top-10 singles ranking, and multiple WTA titles.
- 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_69e11e494eec81909c4d2d51f69499d9 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1577f2f208190ac6270ac4581fa15 |
completed | April 29, 2026, 12:57 a.m. |
Created at: April 16, 2026, 8:43 p.m.