Triple
T8388231
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sophia Lillis |
E197873
|
entity |
| Predicate | portrayed |
P1668
|
FINISHED |
| Object | Gretel |
E487902
|
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: Gretel | Statement: [Sophia Lillis, portrayed, Gretel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gretel Context triple: [Sophia Lillis, portrayed, Gretel]
-
A.
Gretel
chosen
Gretel is a German feminine given name best known from the fairy tale "Hansel and Gretel," where it is used as the name of the young girl protagonist.
-
B.
Helga Gumm
Helga Gumm is a character in the "Spy Kids" film series, known as the grandmother of the Cortez children and a former spy herself.
-
C.
Helga
Helga is a feminine given name of Germanic origin, commonly used in German-speaking and Scandinavian countries.
-
D.
Grete
Grete is the given name of Grete Hermann, a German mathematician and philosopher known for her pioneering work in the foundations of quantum mechanics and computer algebra.
-
E.
Gerda
Gerda is the brave and devoted young heroine of Hans Christian Andersen’s fairy tale who embarks on a perilous journey to rescue her friend Kai from the Snow Queen.
- 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_69ca82f749388190bffbea6dfb509016 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb81090f688190a3a8d1680383c361 |
completed | March 31, 2026, 8:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cde83aac448190b74f65507170a8f7 |
completed | April 2, 2026, 3:53 a.m. |
Created at: March 30, 2026, 6:03 p.m.