Triple
T20486324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hugh Aart Maaskant |
E502601
|
entity |
| Predicate | hasGivenNameForm |
P15846
|
FINISHED |
| Object | Hugh Aart |
—
|
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: Hugh Aart | Statement: [Hugh Aart Maaskant, hasGivenNameForm, Hugh Aart]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hugh Aart Context triple: [Hugh Aart Maaskant, hasGivenNameForm, Hugh Aart]
-
A.
Hugh Aart
chosen
Hugh Aart is the given name of Hugh Aart Maaskant, a notable Dutch architect.
-
B.
Alan Hume
Alan Hume was a British cinematographer known for his work on several James Bond films and other major features such as "Return of the Jedi."
-
C.
Robert Hanhart
Robert Hanhart is a classical philologist and biblical scholar known for his work on the Septuagint and critical editions of ancient Greek texts.
-
D.
Christopher Harter
Christopher Harter is known primarily as the husband of British actor Jeremy Kemp.
-
E.
Willem Darry
Willem Darry is a loyal Targaryen supporter and former knight of the Kingsguard in the world of "A Song of Ice and Fire," known for sheltering and protecting the exiled Targaryen children after Robert's Rebellion.
- 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_69e0b4af32848190aea80682b44d5d6e |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69b5aac208190956c7fd935578d60 |
completed | April 20, 2026, 9:32 p.m. |
Created at: April 16, 2026, 11:34 a.m.