Triple
T22760139
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roger Williams |
E562962
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Till |
—
|
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: Till | Statement: [Roger Williams, notableWork, Till]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Till Context triple: [Roger Williams, notableWork, Till]
-
A.
Till
Till is a character in Anzia Yezierska’s novel "Sapphira and the Slave Girl," contributing to the book’s exploration of race, power, and personal freedom in antebellum America.
-
B.
Till (2022 film)
chosen
Till (2022 film) is a 2022 biographical drama that portrays Mamie Till-Mobley’s pursuit of justice after the racially motivated murder of her 14-year-old son Emmett Till in 1955 Mississippi.
-
C.
Hanna
"Hanna" is a 2011 action thriller film about a teenage girl trained as an assassin, known for its stylized direction and electronic score by The Chemical Brothers.
-
D.
Hanna
Hanna was the wife of the influential 16th-century Jewish legal scholar and codifier Rabbi Joseph Karo.
-
E.
Hanna
Hanna is the central figure in the work "May Night, or the Drowned Maiden," around whom the story’s supernatural and dramatic events revolve.
- 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_69e24552e11c81909c2d61578a558bd7 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17a7b4fe88190b1da25b78f046d13 |
completed | April 29, 2026, 3:26 a.m. |
Created at: April 17, 2026, 3:26 p.m.