Triple
T2297904
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heike Makatsch |
E51658
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | ZDF |
E121600
|
NE 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: ZDF | Statement: [Heike Makatsch, employer, ZDF]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ZDF Context triple: [Heike Makatsch, employer, ZDF]
-
A.
ZDF
chosen
ZDF is Germany’s national public-service television broadcaster, known for producing and co-producing a wide range of news, cultural, and documentary programming.
-
B.
ProSieben
ProSieben is a major German free-to-air television channel known for entertainment programming, international series, and large-scale event broadcasts.
-
C.
Westdeutscher Rundfunk (WDR)
Westdeutscher Rundfunk (WDR) is a major German public broadcasting institution that produces radio, television, and online content primarily for the federal state of North Rhine-Westphalia.
-
D.
ServusTV (historical)
ServusTV (historical) was an Austrian-based television channel that notably broadcast live games and coverage of the Deutsche Eishockey Liga, among other sports and cultural programming.
-
E.
MedienHafen
MedienHafen is a redeveloped former harbor area in Düsseldorf known for its striking contemporary architecture, media and creative industries, and vibrant waterfront nightlife.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a88b0a9f248190bcff941463d8f65a |
completed | March 4, 2026, 7:42 p.m. |
| NER | Named-entity recognition | batch_69abc5df37808190ba6a43dc1e9e723a |
completed | March 7, 2026, 6:29 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae7f2ba4048190898e3524feb0d96d |
completed | March 9, 2026, 8:04 a.m. |
Created at: March 4, 2026, 7:49 p.m.