Triple
T11311964
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James McCudden |
E267857
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | McCudden |
E267857
|
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: McCudden | Statement: [James McCudden, familyName, McCudden]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: McCudden Context triple: [James McCudden, familyName, McCudden]
-
A.
McCudden
chosen
McCudden is a surname most notably associated with James McCudden, a famous British First World War flying ace.
-
B.
Chesley
Chesley is a small rural community in Bruce County, Ontario, Canada, known for its agricultural surroundings and local manufacturing history.
-
C.
Wyle
Wyle is the surname of American actor Noah Wyle, best known for his role as Dr. John Carter on the television series "ER."
-
D.
SkyHawk
SkyHawk is Seagate’s specialized line of hard disk drives designed for surveillance systems, optimized for continuous 24/7 video recording and high reliability.
-
E.
Eaker
Eaker is a surname most notably associated with U.S. Army Air Forces General Ira C. Eaker, a key air power leader during World War II.
- 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_69d6aaca5c24819083db46a30d86cb34 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e9c1b7dc81908d8cc768c47390d3 |
completed | April 9, 2026, 6:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e50a7fc06881909afe85a600d25ff2 |
completed | April 19, 2026, 5:01 p.m. |
Created at: April 8, 2026, 9:32 p.m.