Triple
T9296187
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lea |
E223643
|
entity |
| Predicate | hasSpellingVariant |
P457
|
FINISHED |
| Object | Leia |
E202727
|
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: Leia | Statement: [Lea, hasSpellingVariant, Leia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leia Context triple: [Lea, hasSpellingVariant, Leia]
-
A.
Princess Leia
chosen
Princess Leia is a courageous Rebel leader and princess who becomes one of the central heroes of the original Star Wars trilogy.
-
B.
Leea
Leea is a genus of tropical and subtropical flowering plants traditionally placed in its own family Leeaceae but now often included within the grape family Vitaceae.
-
C.
Beru Lars
Beru Lars is Luke Skywalker’s kind and protective aunt on Tatooine, who helps raise him on the Lars moisture farm in the Star Wars saga.
-
D.
Rey
Rey is the central Force-sensitive protagonist of the Star Wars sequel trilogy, who rises from a scavenger on Jakku to a key figure in the battle between the Jedi and the Sith.
-
E.
Rey
Rey is an ancient city in Iran, now effectively a southern suburb of Tehran, known for its historical and archaeological significance.
- 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_69ca8423edb08190bc0c91287a484768 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd089c9c588190967404c9eb938dfb |
completed | April 1, 2026, 11:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0c7717f30819095fc3e6e4f765790 |
completed | April 4, 2026, 8:10 a.m. |
Created at: March 30, 2026, 7:36 p.m.