Triple
T3327058
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joachim |
E69939
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object | Joachim Gauck |
E31137
|
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: Joachim Gauck | Statement: [Joachim, hasNotableBearer, Joachim Gauck]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joachim Gauck Context triple: [Joachim, hasNotableBearer, Joachim Gauck]
-
A.
Joachim Gauck
chosen
Joachim Gauck is a German Protestant pastor, former civil rights activist in East Germany, and the 11th President of Germany, serving from 2012 to 2017.
-
B.
Frank-Walter Steinmeier
Frank-Walter Steinmeier is a German politician and diplomat who has served as the President of Germany since 2017 and was previously the country’s foreign minister.
-
C.
Johannes Rau
Johannes Rau was a German Social Democratic politician who served as President of Germany from 1999 to 2004 and previously as Minister-President of North Rhine-Westphalia.
-
D.
Roman Herzog
Roman Herzog was a German jurist and politician who served as President of Germany from 1994 to 1999.
-
E.
Bernhard Scholz
Bernhard Scholz is a German computer scientist known for his work in programming languages, logic programming, and the development of the Soufflé Datalog engine.
- 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_69ad85a1829881908942c14075644d0d |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb16dc170819086a63e033e17d8b3 |
completed | March 8, 2026, 5:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b31a7ce34c81908df0c30a41fd925c |
completed | March 12, 2026, 7:56 p.m. |
Created at: March 8, 2026, 3:12 p.m.