Triple
T14167378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crossing Delancey |
E351113
|
entity |
| Predicate | starred |
P5563
|
FINISHED |
| Object | Jeroen Krabbé |
E306272
|
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: Jeroen Krabbé | Statement: [Crossing Delancey, starred, Jeroen Krabbé]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jeroen Krabbé Context triple: [Crossing Delancey, starred, Jeroen Krabbé]
-
A.
Jeroen Krabbé
chosen
Jeroen Krabbé is a Dutch actor and director known internationally for his roles in films such as "The Living Daylights," "The Fugitive," and "Ocean's Twelve."
-
B.
Willem Vos
Willem Vos is a Dutch classical percussionist and marimba player known for his performances and recordings in contemporary and chamber music.
-
C.
Willem Kes
Willem Kes was a Dutch conductor and violinist best known as the founding conductor and organizer of the Royal Concertgebouw Orchestra in Amsterdam.
-
D.
Thijs Lauer
Thijs Lauer is the son of former American television news anchor Matt Lauer.
-
E.
Martijn Krabbé
Martijn Krabbé is a Dutch television presenter best known for hosting popular talent and reality shows in the Netherlands.
- 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_69d8278775fc8190b0802d22ca2f495d |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61b355f08190864c7322bbcb766d |
completed | April 14, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcf7f57ad88190aeb8ee0f834bfa20 |
completed | May 7, 2026, 8:37 p.m. |
Created at: April 10, 2026, 1 a.m.