Triple
T2136047
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lita Grey |
E46655
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Lita Grey |
E46655
|
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: Lita Grey | Statement: [Lita Grey, name, Lita Grey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lita Grey Context triple: [Lita Grey, name, Lita Grey]
-
A.
Lita Grey
chosen
Lita Grey was an American actress best known for her early silent-film work and her highly publicized, scandalous marriage to Charlie Chaplin as a teenager.
-
B.
Leona Vicario
Leona Vicario was a prominent Mexican independence heroine, journalist, and supporter of the insurgent cause against Spanish rule in the early 19th century.
-
C.
Diandra Luker
Diandra Luker is a film producer and the former wife of American actor Michael Douglas.
-
D.
Chantay Savage
Chantay Savage is an American R&B singer and songwriter best known for her soulful vocals and 1990s hits like her cover of "I Will Survive."
-
E.
Krystle Campbell
Krystle Campbell was a young American woman from Massachusetts who was killed in the 2013 Boston Marathon bombing and became one of its most widely remembered victims.
- 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_69a88a174ab48190a5db20c132e5dccf |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abbdc4ce8c81908d143d5451681e6a |
completed | March 7, 2026, 5:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae51acc0f88190a580e29d887170ec |
completed | March 9, 2026, 4:50 a.m. |
Created at: March 4, 2026, 7:44 p.m.