Triple
T2218075
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Christopher Isherwood |
E48077
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Isherwood |
E48077
|
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: Isherwood | Statement: [Christopher Isherwood, familyName, Isherwood]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Isherwood Context triple: [Christopher Isherwood, familyName, Isherwood]
-
A.
Christopher Isherwood
chosen
Christopher Isherwood was a 20th-century Anglo-American novelist and playwright best known for works like "Goodbye to Berlin," which inspired the musical "Cabaret."
-
B.
Harold Chestnut
Harold Chestnut was an American engineer and control systems pioneer known for his influential work in automation and leadership within the IEEE.
-
C.
Hamar Greenwood
Hamar Greenwood was a British politician and the last Chief Secretary for Ireland, known for his controversial role during the Irish War of Independence and the Anglo-Irish Treaty period.
-
D.
Bewkes
Bewkes is the surname of Jeff Bewkes, the American media executive best known for serving as CEO of Time Warner.
-
E.
Shaw
Shaw is a historic, culturally rich neighborhood in Washington, D.C., known for its African American heritage, jazz legacy, and vibrant urban revival.
- 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_69a88aa1ee708190862c8c378c41e9eb |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc010bd4c8190ace293b37eac1de5 |
completed | March 7, 2026, 6:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae6afc6dd881909dd51d8a18ab4c74 |
completed | March 9, 2026, 6:38 a.m. |
Created at: March 4, 2026, 7:46 p.m.