Triple
T13763573
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joost de Blank |
E330676
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Joost |
E102852
|
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: Joost | Statement: [Joost de Blank, givenName, Joost]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joost Context triple: [Joost de Blank, givenName, Joost]
-
A.
Joost
chosen
Joost is a masculine given name of Dutch origin, historically associated with figures such as the poet and playwright Joost van den Vondel.
-
B.
Joost
Joost was an online video distribution service and Internet TV platform co-created by Skype and Kazaa co-founder Niklas Zennström.
-
C.
Joost Lips
Joost Lips was a Flemish humanist and classical scholar of the late Renaissance, renowned for his influential works on Stoic philosophy and Roman history.
-
D.
Jelle
Jelle is a Dutch given name commonly used for males, particularly in the Netherlands and Friesland.
-
E.
Joost Vos
Joost Vos is a Dutch architect best known as a leading partner at the renowned architecture firm Benthem Crouwel Architekten, contributing to major public and infrastructural projects.
- 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_69d81c583b0081909e408a17db517a21 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de022690ac8190bd5410ecc659a2a7 |
completed | April 14, 2026, 9 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7a862e6808190b8fbb27304212058 |
completed | May 3, 2026, 7:56 p.m. |
Created at: April 9, 2026, 10:10 p.m.