Triple
T22792361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hank Stram |
E564144
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Henry |
—
|
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: Henry | Statement: [Hank Stram, givenName, Henry]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Henry Context triple: [Hank Stram, givenName, Henry]
-
A.
Henry
Henry was a French royal prince who served as Archbishop of Reims, a prominent ecclesiastical and political position in medieval France.
-
B.
Henry
Henry "Raleigh" Gordon was an American musician best known as a member of the 1950s doo-wop group The Red Caps.
-
C.
Henry
Henry is the given name of Gotthilf Henry Ernest Muhlenberg, an American Lutheran clergyman and pioneering botanist known for his work in early American plant taxonomy.
-
D.
Henry
chosen
Henry is the given first name of H. Frederick Gregory, an American NASA astronaut and former Air Force test pilot.
-
E.
Henry
Henry is the middle name of John Henry Moore, an American politician and jurist who served as a United States federal judge.
- 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_69e2458185f88190b0045227ee420411 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17cd5778c81909a18317ff98e341c |
completed | April 29, 2026, 3:36 a.m. |
Created at: April 17, 2026, 3:30 p.m.