Triple
T22618718
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Willi Graf |
E558215
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Graf |
—
|
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: Graf | Statement: [Willi Graf, familyName, Graf]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Graf Context triple: [Willi Graf, familyName, Graf]
-
A.
Graf
chosen
Graf is a historical German noble title roughly equivalent to a count in other European aristocratic systems.
-
B.
Grafh
Grafh is an American rapper from Queens, New York, known for his gritty lyricism and work in the underground hip-hop scene.
-
C.
Gráfelli
Gráfelli is one of the highest and most prominent mountains on the Faroe Islands, located on the island of Eysturoy.
-
D.
Grafengehaig
Grafengehaig is a small rural municipality in the Kulmbach district of northern Bavaria, Germany.
-
E.
Gsell
Gsell is a surname of Germanic origin borne by various notable individuals, including artists, scholars, and public figures.
- 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_69e24545a8e08190bfa7482a2c725ff1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f16e377ae88190832edfdfbc3ed58f |
completed | April 29, 2026, 2:34 a.m. |
Created at: April 17, 2026, 3 p.m.