Triple
T4953508
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1. FC Heidenheim |
E111224
|
entity |
| Predicate | headCoach |
P256
|
FINISHED |
| Object | Frank Schmidt |
E394325
|
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: Frank Schmidt | Statement: [1. FC Heidenheim, headCoach, Frank Schmidt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frank Schmidt Context triple: [1. FC Heidenheim, headCoach, Frank Schmidt]
-
A.
Frank Schmidt
chosen
Frank Schmidt is a German football manager and former defender best known for his long-term tenure transforming 1. FC Heidenheim from lower leagues into a Bundesliga club.
-
B.
Paul Schmidt
Paul Schmidt is a relatively common personal name shared by multiple notable individuals across fields such as science, sports, and the arts.
-
C.
Walter Scheib
Walter Scheib was an American chef best known for serving as the White House Executive Chef for the Clinton and George W. Bush administrations.
-
D.
Ron Schmidt
Ron Schmidt is a television producer best known for his executive production work on major series such as the Game of Thrones prequel "House of the Dragon."
-
E.
Harold Schmidt
Harold Schmidt is a relatively obscure individual whose name is shared with several people, including professionals in fields such as sports, academia, and the arts.
- 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_69bd4418390c8190b7e9766a2512ce55 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd71b82dd88190adfb08c3b3191fe0 |
completed | March 20, 2026, 4:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69beb0daa53481908c705ca3698ab777 |
completed | March 21, 2026, 2:53 p.m. |
Created at: March 20, 2026, 1:31 p.m.