Triple
T12613111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Gangster |
E301178
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Belita |
E894932
|
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: Belita | Statement: [The Gangster, starring, Belita]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Belita Context triple: [The Gangster, starring, Belita]
-
A.
Belita
chosen
Belita was a British Olympic figure skater and film actress known for her graceful performances in 1940s and 1950s Hollywood ice-skating musicals.
-
B.
Bauline
Bauline is a small coastal town in Newfoundland and Labrador, Canada, located on the Avalon Peninsula near St. John’s.
-
C.
Sheilia
Sheilia is a feminine given name, typically considered an alternative spelling of the name Sheila.
-
D.
Arnissa
Arnissa is a small town in northern Greece situated close to Lake Vegoritida, known for its scenic lakeside setting and surrounding natural landscape.
-
E.
Alithea
Alithea is a virtuous and intelligent gentlewoman in William Wycherley’s Restoration comedy "The Country Wife," whose moral integrity contrasts with the play’s surrounding hypocrisy and sexual intrigue.
- 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_69d7bdeaf49c8190b13800111fa77ea3 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d960c2e5b88190a7cc16002b218d8a |
completed | April 10, 2026, 8:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f65ed1044c8190bbe881d32a4bf29e |
completed | May 2, 2026, 8:30 p.m. |
Created at: April 9, 2026, 5:12 p.m.