Triple
T10463112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shakira Caine |
E246724
|
entity |
| Predicate | hasTitle |
P38
|
FINISHED |
| Object | Lady Caine |
E866155
|
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: Lady Caine | Statement: [Shakira Caine, hasTitle, Lady Caine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lady Caine Context triple: [Shakira Caine, hasTitle, Lady Caine]
-
A.
Lady Caine
chosen
Lady Caine is Shakira Caine, a Guyanese-British former fashion model and actress best known as the wife of English actor Sir Michael Caine.
-
B.
Lady Steyn
Lady Steyn is the wife of Lord Steyn, a prominent British Law Lord and jurist.
-
C.
Lady Larken
Lady Larken is a romantic, high-strung noblewoman in the musical comedy "Once Upon a Mattress," whose secret pregnancy drives much of the plot’s urgency and humor.
-
D.
Sibyl Marshal
Sibyl Marshal was a 13th-century Anglo-Norman noblewoman and daughter of the famed knight and statesman William Marshal, 1st Earl of Pembroke.
-
E.
Lady Jaspers
Lady Jaspers is the name used for the women’s athletic teams representing Manhattan College in intercollegiate sports.
- 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_69d381c16c248190a2fe5b471e584e9c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d50884fac48190af22e181b1492557 |
completed | April 7, 2026, 1:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d8dc4fbc3481909b214137f26e243b |
completed | April 10, 2026, 11:17 a.m. |
Created at: April 6, 2026, 12:19 p.m.