Triple
T10408745
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | I Am a Camera |
E245332
|
entity |
| Predicate | hasCharacter |
P2308
|
FINISHED |
| Object | Sally Bowles |
E518345
|
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: Sally Bowles | Statement: [I Am a Camera, hasCharacter, Sally Bowles]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sally Bowles Context triple: [I Am a Camera, hasCharacter, Sally Bowles]
-
A.
Sally Bowles
chosen
Sally Bowles is a hedonistic, free-spirited nightclub singer in 1930s Berlin, best known as the central character of the musical and film "Cabaret."
-
B.
cabaret singer Maude Maggart
Maude Maggart is an American cabaret singer known for her intimate, nostalgic interpretations of early 20th-century popular songs and standards.
-
C.
Nelly Kröger
Nelly Kröger was the second wife of German novelist Heinrich Mann, known primarily through her connection to his life and literary circle.
-
D.
Hildy Beyeler
Hildy Beyeler is a Swiss art patron known for co-founding the renowned Beyeler Foundation Museum, which houses one of Europe’s leading collections of modern and contemporary art.
-
E.
Cecelia Halpert
Cecelia Halpert is the daughter of Jim and Pam Halpert on the U.S. television series "The Office."
- 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_69d381be340c8190b05998703d42d224 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9faa97c819092cadedadabe26bf |
completed | April 7, 2026, 11:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d87e9084fc81909e1d46a111a1ef2b |
completed | April 10, 2026, 4:37 a.m. |
Created at: April 6, 2026, 12:09 p.m.