Triple
T4207090
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Lady Vanishes |
E93808
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Paul Lukas |
E224153
|
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: Paul Lukas | Statement: [The Lady Vanishes, starring, Paul Lukas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Lukas Context triple: [The Lady Vanishes, starring, Paul Lukas]
-
A.
Paul Lukas
chosen
Paul Lukas was a Hungarian-American actor known for his distinguished stage and film career, including an Academy Award-winning performance in "Watch on the Rhine."
-
B.
Joseph Markovitch
Joseph Markovitch was the father of French photographer and painter Dora Maar, a key figure in the Surrealist movement and companion of Pablo Picasso.
-
C.
Paul Seydor
Paul Seydor is a film editor and scholar best known for his work on Sam Peckinpah’s films and his writings on American cinema.
-
D.
Walter Abel
Walter Abel was an American stage, film, and television character actor active from the silent era through the mid-20th century.
-
E.
Peter Hermann
Peter Hermann is an American actor and producer best known for his roles on television series such as "Law & Order: Special Victims Unit" and "Younger."
- 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_69b3451743608190808f41d17ccf2650 |
completed | March 12, 2026, 10:58 p.m. |
| NER | Named-entity recognition | batch_69b3480cfacc81909a2705eb4e9ce8c1 |
completed | March 12, 2026, 11:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b59628da008190ae0e458ed3a5890b |
completed | March 14, 2026, 5:08 p.m. |
Created at: March 12, 2026, 11:03 p.m.