Triple
T21510628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lukas Heller |
E530708
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Lukas Heller |
E530708
|
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: Lukas Heller | Statement: [Lukas Heller, name, Lukas Heller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lukas Heller Context triple: [Lukas Heller, name, Lukas Heller]
-
A.
Lukas Heller
chosen
Lukas Heller was a German-born British screenwriter best known for his work on psychological thrillers and film adaptations in the 1960s and 1970s.
-
B.
Lukas Ettlin
Lukas Ettlin is a Swiss-born cinematographer and director known for his work on feature films and television series, including action and genre projects.
-
C.
Mathias Gnädinger
Mathias Gnädinger was a prominent Swiss actor known for his powerful character roles in film, television, and theater.
-
D.
Lucas Beyer
Lucas Beyer is a machine learning researcher known for co-authoring the Vision Transformer (ViT) model that applied transformer architectures to image recognition.
-
E.
Lukas Haas
Lukas Haas is an American actor known for his early breakthrough role in "Witness" (1985) and a diverse career spanning independent films and major Hollywood productions.
- 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_69e0c45c81f08190a6b8bbb70a45aae7 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea84dfbc8190a23d9a7d6eb2c2b5 |
completed | April 23, 2026, 9:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09e143c73081908ace3b52a18bdf98 |
completed | May 17, 2026, 3:39 p.m. |
Created at: April 16, 2026, 6:25 p.m.