Triple
T20785934
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walraven van Hall |
E511636
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Gijs van Hall |
—
|
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: Gijs van Hall | Statement: [Walraven van Hall, relative, Gijs van Hall]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gijs van Hall Context triple: [Walraven van Hall, relative, Gijs van Hall]
-
A.
Gijs van Hall
chosen
Gijs van Hall was a Dutch banker and politician who served as Mayor of Amsterdam in the 1950s and 1960s.
-
B.
Lodewijk van den Berg
Lodewijk van den Berg is a Dutch-born American chemical engineer and astronaut who flew as a payload specialist on NASA's Space Shuttle Challenger.
-
C.
Piet de Jong
Piet de Jong was a Dutch politician who served as Prime Minister of the Netherlands from 1967 to 1971.
-
D.
Pieter Platevoet
Pieter Platevoet, better known by his Latinized name Petrus Plancius, was a Flemish-Dutch astronomer, cartographer, and clergyman who played a key role in early Dutch navigation and mapmaking during the Age of Discovery.
-
E.
Hendrik de Vries
Hendrik de Vries was a mathematician who supervised and mentored the influential algebraist Bartel Leendert van der Waerden.
- 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_69e0b4cb83948190bd57bec21d78ed53 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c28c0d0c8190aa48e6fdfdaab750 |
completed | April 21, 2026, 12:19 a.m. |
Created at: April 16, 2026, 12:38 p.m.