Triple
T18203452
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Bohm |
E435847
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Bohm |
—
|
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: Bohm | Statement: [David Bohm, familyName, Bohm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bohm Context triple: [David Bohm, familyName, Bohm]
-
A.
Böhm
chosen
Böhm is a German-language surname borne by numerous notable figures in fields such as music, philosophy, and science.
-
B.
Hark Bohm
Hark Bohm is a German actor, director, and screenwriter known for his collaborations with filmmaker Fatih Akin and his contributions to New German Cinema.
-
C.
Bohmte
Bohmte is a small municipality in Lower Saxony, Germany, known for its rural character and innovative traffic-calming street design.
-
D.
Von Bohm
Von Bohm is a central character in Rainer Werner Fassbinder’s film "Lola," serving as an idealistic building commissioner whose moral rigidity clashes with the corruption and decadence of the town he tries to reform.
-
E.
Martin Bohm
Martin Bohm is the widowed former journalist and father at the heart of the TV series "Touch," struggling to connect with his emotionally challenged, seemingly mute son who can predict future events through complex number patterns.
- 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_69d8b90dba6481908e119eb9aa4ca0cb |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e221bbbc819088a7559a46b7d4e7 |
completed | April 19, 2026, 2:09 p.m. |
Created at: April 10, 2026, 10:32 a.m.