Triple
T19853956
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stefan |
E477080
|
entity |
| Predicate | hasDiminutive |
P456
|
FINISHED |
| Object | Steffi |
—
|
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: Steffi | Statement: [Stefan, hasDiminutive, Steffi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Steffi Context triple: [Stefan, hasDiminutive, Steffi]
-
A.
Steffi
chosen
Steffi is a diminutive form of the given name Stephan, commonly used as a familiar or affectionate nickname.
-
B.
Steffi Duna
Steffi Duna was a Hungarian-born film and stage actress and dancer active in Hollywood during the 1930s and 1940s, known for her exotic roles and musical performances.
-
C.
Fran Striker
Fran Striker was an American writer and radio producer best known for creating iconic adventure characters such as the Lone Ranger and the Green Hornet.
-
D.
Martina Gedeck
Martina Gedeck is a German actress acclaimed for her versatile performances in film and television, including prominent roles in internationally recognized dramas.
-
E.
Annika Backes
Annika Backes is an American model known for her work in fashion and for being married to Dutch DJ and producer Tiësto.
- 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_69d8e51d39d081909bcfafeaaf3d2fcc |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6586aa1dc8190b6cfe051a57e338b |
completed | April 20, 2026, 4:46 p.m. |
Created at: April 10, 2026, 1:51 p.m.