Triple
T17672743
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Char |
E440564
|
entity |
| Predicate | shortFormOf |
P43
|
FINISHED |
| Object | Charlize |
—
|
NE NERFINISHED |
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: Charlize | Statement: [Char, shortFormOf, Charlize]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Charlize Context triple: [Char, shortFormOf, Charlize]
-
A.
Charlize
chosen
Charlize is a feminine given name, most famously borne by South African–born actress and producer Charlize Theron.
-
B.
Charlyn
Charlyn is the birth name of American singer-songwriter and musician Chan Marshall, best known by her stage name Cat Power.
-
C.
Nicole
Nicole is a feminine given name of Greek origin meaning "victory of the people," commonly used in many English- and French-speaking countries.
-
D.
Nicole
Nicole is a fictional character played by English actress Kelly Reilly, known from her work in film and television dramas.
-
E.
Nicole
Nicole is a central character in the dark comedy-drama film "Hesher," serving as a key emotional anchor in the story’s exploration of grief and unconventional relationships.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9e87e18819087104a44dc4dc5b1 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e46f6aa64081908c9a82128a5a9024 |
completed | April 19, 2026, 6 a.m. |
Created at: April 10, 2026, 10 a.m.