Triple
T20005867
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jodi Balfour |
E494458
|
entity |
| Predicate | appearedIn |
P795
|
FINISHED |
| Object | The Crown |
—
|
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: The Crown | Statement: [Jodi Balfour, appearedIn, The Crown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Crown Context triple: [Jodi Balfour, appearedIn, The Crown]
-
A.
The Crown
The Crown is the popular nickname for Charlotte FC, the Major League Soccer club based in Charlotte, North Carolina.
-
B.
The Crown
The Crown is a traditional English pub located in the village of Turners Hill in West Sussex.
-
C.
The Crown
The Crown is a stage play, distinct from the popular television series, whose narrative and themes center on issues of power, authority, and leadership.
-
D.
The Crown
chosen
The Crown is a critically acclaimed historical drama television series that chronicles the reign of Queen Elizabeth II and the political and personal events that shaped the second half of the 20th century.
-
E.
the Crown
The Crown is the symbolic and legal embodiment of the British monarchy and state authority.
- 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_69da626b2d748190886981ea90c8b2ea |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e661a57ef881909115c8aa232b1012 |
completed | April 20, 2026, 5:25 p.m. |
Created at: April 11, 2026, 3:33 p.m.