Triple
T11202348
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ralph Sampson |
E265070
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Sampson |
E64583
|
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: Sampson | Statement: [Ralph Sampson, familyName, Sampson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sampson Context triple: [Ralph Sampson, familyName, Sampson]
-
A.
Sampson
chosen
Sampson is a surname most notably associated with William T. Sampson, a U.S. Navy admiral prominent during the Spanish–American War.
-
B.
Abner
Abner is a prominent Old Testament military commander and political figure in the Hebrew Bible, known especially for his role in the power struggles following King Saul’s death.
-
C.
Gomer
Gomer is a biblical figure traditionally regarded as a descendant of Japheth and an ancestral nation mentioned in Old Testament prophetic writings.
-
D.
Scroop
Scroop is a given name most notably borne by Scroop Egerton, 1st Duke of Bridgewater, an English nobleman of the late 17th and early 18th centuries.
-
E.
Gulley Jimson
Gulley Jimson is a disreputable, obsessive, and eccentric aging painter who serves as the roguish antihero of Joyce Cary’s comic novel "The Horse’s Mouth."
- 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_69d6aa9eb9248190b20211772621b4bc |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8c36c188190bfa4d5f8e6cbbbea |
completed | April 9, 2026, 5:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4971d537c8190ab53a2ca18d643f3 |
completed | April 19, 2026, 8:49 a.m. |
Created at: April 8, 2026, 9:29 p.m.