Triple
T11493838
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hotel Berlin |
E272482
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Raymond Massey |
E182105
|
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: Raymond Massey | Statement: [Hotel Berlin, castMember, Raymond Massey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Raymond Massey Context triple: [Hotel Berlin, castMember, Raymond Massey]
-
A.
Raymond Massey
chosen
Raymond Massey was a Canadian-American actor known for his commanding screen presence and memorable roles in classic films and stage productions.
-
B.
Clifton Webb
Clifton Webb was an American actor, dancer, and singer best known for his sophisticated, often acerbic screen persona in films such as "Laura" and "Sitting Pretty."
-
C.
Hugh Sothern
Hugh Sothern was an American character actor active in early 20th-century stage and film, known for supporting roles in Hollywood movies.
-
D.
Adolphe Menjou
Adolphe Menjou was an American actor known for his suave, debonair screen persona and prominent roles in early Hollywood films, including both silent and sound-era classics.
-
E.
George Shields
George Shields is a personal name shared by multiple individuals, including figures in fields such as politics, law, and academia.
- 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_69d6aae1b09881909ce2ded3fa0c14fa |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d85ddffdf88190a00e94ad5b8b91a5 |
completed | April 10, 2026, 2:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ee86853e088190a9c1378aad45fa18 |
completed | April 26, 2026, 9:41 p.m. |
Created at: April 8, 2026, 9:36 p.m.