Triple
T12749985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hermann Kosterlitz |
E304704
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Three Smart Girls |
E304705
|
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: Three Smart Girls | Statement: [Hermann Kosterlitz, notableWork, Three Smart Girls]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Three Smart Girls Context triple: [Hermann Kosterlitz, notableWork, Three Smart Girls]
-
A.
Three Smart Girls
chosen
Three Smart Girls is a 1936 American musical comedy film that helped launch Deanna Durbin to stardom and played a key role in revitalizing Universal Pictures’ fortunes.
-
B.
Three Wise Girls
Three Wise Girls is a 1932 American pre-Code romantic drama film best known for featuring early performances by Jean Harlow and Mae Clarke.
-
C.
Calendar Girls
Calendar Girls is a 2003 British comedy-drama film, inspired by a true story, about a group of middle-aged women who pose nude for a charity calendar.
-
D.
Very Good Girls
Very Good Girls is a 2013 coming-of-age drama film about two best friends whose bond is tested when they fall for the same young man.
-
E.
Light Girls
Light Girls is a documentary film that explores the experiences, challenges, and cultural perceptions surrounding light-skinned Black women.
- 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_69d7bdf1fcd081909ffb0e0d6fa3a07d |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96bd75f508190aaae0969f33d1523 |
completed | April 10, 2026, 9:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f67c964c508190b4d6a094b388280b |
completed | May 2, 2026, 10:37 p.m. |
Created at: April 9, 2026, 5:27 p.m.