Triple
T22962080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | In Search of Fellini |
E570927
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object |
Enrico Oetiker
Enrico Oetiker is an actor known for his role in the film "In Search of Fellini."
|
E1563997
|
NE FINISHED |
How this triple was built (4 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: Enrico Oetiker | Statement: [In Search of Fellini, castMember, Enrico Oetiker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Enrico Oetiker Context triple: [In Search of Fellini, castMember, Enrico Oetiker]
-
A.
Bruno Wechner
Bruno Wechner was an Austrian Roman Catholic prelate who became the inaugural bishop of the Diocese of Feldkirch.
-
B.
Bernhard Wicki
Bernhard Wicki was an Austrian-Swiss film director and actor best known for his anti-war films and his co-direction of the World War II epic "The Longest Day."
-
C.
Ernst Torgler
Ernst Torgler was a German Communist politician who became widely known as a principal defendant in the 1933 Reichstag fire trial under the Nazi regime.
-
D.
Rainer Stahel
Rainer Stahel was a German Wehrmacht officer and city commandant during World War II, known for his roles in urban defensive operations on the Eastern Front.
-
E.
Andreas Maurer
Andreas Maurer was a mountaineer known for making the first recorded ascent of the Alpine peak Mont Maudit in the Mont Blanc massif.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Enrico Oetiker Triple: [In Search of Fellini, castMember, Enrico Oetiker]
Generated description
Enrico Oetiker is an actor known for his role in the film "In Search of Fellini."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Enrico Oetiker Target entity description: Enrico Oetiker is an actor known for his role in the film "In Search of Fellini."
-
A.
Bruno Wechner
Bruno Wechner was an Austrian Roman Catholic prelate who became the inaugural bishop of the Diocese of Feldkirch.
-
B.
Bernhard Wicki
Bernhard Wicki was an Austrian-Swiss film director and actor best known for his anti-war films and his co-direction of the World War II epic "The Longest Day."
-
C.
Ernst Torgler
Ernst Torgler was a German Communist politician who became widely known as a principal defendant in the 1933 Reichstag fire trial under the Nazi regime.
-
D.
Rainer Stahel
Rainer Stahel was a German Wehrmacht officer and city commandant during World War II, known for his roles in urban defensive operations on the Eastern Front.
-
E.
Andreas Maurer
Andreas Maurer was a mountaineer known for making the first recorded ascent of the Alpine peak Mont Maudit in the Mont Blanc massif.
- F. None of above. chosen
Provenance (5 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_69e245b212a88190b5259caf51606084 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f181f594fc8190816418486b798198 |
completed | April 29, 2026, 3:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0bca20c2a08190bbce57b5c9d393e2 |
completed | May 19, 2026, 2:25 a.m. |
| NEDg | Description generation | batch_6a0bcb6a202c819081e76d7af5c7eb71 |
completed | May 19, 2026, 2:31 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0bcc282774819080b041bc82fca561 |
completed | May 19, 2026, 2:34 a.m. |
Created at: April 17, 2026, 3:47 p.m.