Triple
T22395924
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Love and Monsters |
E553628
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Marcus Trumpp |
—
|
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: Marcus Trumpp | Statement: [Love and Monsters, musicBy, Marcus Trumpp]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marcus Trumpp Context triple: [Love and Monsters, musicBy, Marcus Trumpp]
-
A.
Marcus Trumpp
chosen
Marcus Trumpp is a film composer known for his work on the horror movie "Fear Street Part Three: 1666."
-
B.
Philipp Schwartzerdt
Philipp Schwartzerdt, better known as Philip Melanchthon, was a leading German humanist and key collaborator of Martin Luther in the Protestant Reformation.
-
C.
Alexander Heppe
Alexander Heppe is a German local politician who serves as the mayor of the town of Eschwege.
-
D.
Maxe Baumann
Maxe Baumann is a popular East German television comedy character from the GDR era, known from the eponymous series about a grumpy but warm-hearted retiree and his family.
-
E.
Matthias Grunsky
Matthias Grunsky is an Austrian cinematographer known for his long-time collaboration with director Andrew Bujalski on acclaimed independent films.
- 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_69e11e4da7048190b4387d422a9a0de5 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1585e84b081908c95ed3e0d987ed8 |
completed | April 29, 2026, 1:01 a.m. |
Created at: April 16, 2026, 8:45 p.m.