Triple
T17284850
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Horst Seehofer |
E419626
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Horst |
E895437
|
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: Horst | Statement: [Horst Seehofer, givenName, Horst]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Horst Context triple: [Horst Seehofer, givenName, Horst]
-
A.
Horst
Horst is the taxpayer involved as the respondent in the landmark U.S. Supreme Court tax case Helvering v. Horst, which helped define the assignment-of-income doctrine.
-
B.
Horst
Horst is a tough, intimidating sous-chef in the animated film "Ratatouille," known for his mysterious and often contradictory criminal backstories.
-
C.
Horst
chosen
Horst is a masculine German given name commonly used in German-speaking countries.
-
D.
Hohberg
Hohberg is a municipality in the Ortenau district of Baden-Württemberg in southwestern Germany.
-
E.
Erasbach
Erasbach is a small locality in Bavaria, Germany, best known as the birthplace of the composer Christoph Willibald Gluck.
- 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_69d886da626481908a14ce7830329a35 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e4332cabdc8190bbc711ab806d53bf |
completed | April 19, 2026, 1:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0180d29f4881908694f0182930d716 |
completed | May 11, 2026, 7:10 a.m. |
Created at: April 10, 2026, 5:40 a.m.