Triple
T4857391
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hans Hahn |
E108569
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Hahn |
E172540
|
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: Hahn | Statement: [Hans Hahn, familyName, Hahn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hahn Context triple: [Hans Hahn, familyName, Hahn]
-
A.
Hahn
chosen
Hahn is a surname of German origin borne by various notable individuals across fields such as science, sports, and the arts.
-
B.
Hansi
Hansi is a historic town in the Hisar district of Haryana, India, known for its ancient forts and archaeological significance.
-
C.
Hauke
Hauke is a Germanic given name, particularly common in Northern Germany, that is cognate with the English name Hugh.
-
D.
Klamm
Klamm is a powerful, elusive bureaucratic official in Franz Kafka’s novel "The Castle," symbolizing opaque and inaccessible authority.
-
E.
Heurich
Heurich is a German surname most notably associated with Christian Heurich, a prominent brewer and businessman in Washington, D.C.
- 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_69bd440a89548190a5f14ba6da6b97dc |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6d3f24688190b2f2b79bcde96973 |
completed | March 20, 2026, 3:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be5cec638481909a3345f348116bbc |
completed | March 21, 2026, 8:55 a.m. |
Created at: March 20, 2026, 1:26 p.m.