Triple
T20613781
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | English College, Rome |
E506513
|
entity |
| Predicate | founder |
P104
|
FINISHED |
| Object | William Allen |
—
|
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: William Allen | Statement: [English College, Rome, founder, William Allen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: William Allen Context triple: [English College, Rome, founder, William Allen]
-
A.
William Allen
chosen
William Allen was a 16th-century English Cardinal and leading Catholic figure who played a key role in the Counter-Reformation and the support of English Catholic exiles.
-
B.
William Allen
William Allen is a songwriter known for his work on the musical score for the 2004 film "If."
-
C.
William Allen
William Allen was an 18th-century colonial-era merchant, lawyer, and Chief Justice of Pennsylvania who became one of the colony’s wealthiest and most influential figures.
-
D.
William Frederick Allen
William Frederick Allen was a 19th-century American civil engineer and railroad executive best known for helping standardize North American railway time.
-
E.
Andrew Ellicott
Andrew Ellicott was an American surveyor and cartographer known for his work mapping the boundaries of the early United States, including completing the survey of the District of Columbia.
- 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_69e0b4bb2b4081908fa4a72444120f35 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6aada19e481909363428ceda67603 |
completed | April 20, 2026, 10:38 p.m. |
Created at: April 16, 2026, 11:41 a.m.