Triple
T8441853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walter Hill |
E199367
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Hill |
E119957
|
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: Hill | Statement: [Walter Hill, familyName, Hill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hill Context triple: [Walter Hill, familyName, Hill]
-
A.
Hill
chosen
Hill is a common English surname of Anglo-Saxon origin, typically referring to someone who lived near or on a hill.
-
B.
How Hill
How Hill is a scenic area in the Norfolk Broads of England, known for its marshland nature reserve, historic drainage mills, and the thatched How Hill House overlooking the River Ant.
-
C.
Hill East
Hill East is a residential neighborhood in Southeast Washington, D.C., known for its rowhouses, proximity to the Anacostia River, and easy access to Capitol Hill and downtown.
-
D.
Harrison Hill
Harrison Hill is a wealthy and charismatic New York advertising executive who becomes the central figure in the mystery-thriller film "Perfect Stranger."
-
E.
High Hill
High Hill, also known as Jaynes Hill, is the highest natural point on Long Island in New York State.
- 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_69ca8314cd6c8190a6b8c2a1096e18f3 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe30fba4081908bfdef3faf5baceb |
completed | March 31, 2026, 3:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce1da3a99481909c9beae665bb5b83 |
completed | April 2, 2026, 7:41 a.m. |
Created at: March 30, 2026, 6:08 p.m.