Triple
T20127911
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Circle |
E490805
|
entity |
| Predicate | protagonist |
P268
|
FINISHED |
| Object | Mae Holland |
—
|
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: Mae Holland | Statement: [The Circle, protagonist, Mae Holland]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mae Holland Context triple: [The Circle, protagonist, Mae Holland]
-
A.
Mae Holland
chosen
Mae Holland is the protagonist of Dave Eggers' dystopian novel "The Circle," a young woman who becomes increasingly entangled in the culture and power of a dominant tech corporation.
-
B.
Jane Holland
Jane Holland was the wife of Australian-born British actor Leo McKern.
-
C.
Jane English
Jane English is a screenwriter best known for co-writing the British 3D dance film "StreetDance 3D."
-
D.
Anne Douglas
Anne Douglas was a German-born Belgian-American film producer and philanthropist best known as the longtime wife and partner of actor Kirk Douglas.
-
E.
Charlotte Holland
Charlotte Holland was a British actress and radio presenter, best known for her work on BBC radio and as the mother of actress Zoë Wanamaker.
- 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_69da62651a0c8190a3e05e95e056a66b |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6675fe3d48190b0c20b483a951e68 |
completed | April 20, 2026, 5:50 p.m. |
Created at: April 11, 2026, 11:31 p.m.