Triple
T10828182
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lambert Meertens |
E255545
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | CWI |
E51000
|
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: CWI | Statement: [Lambert Meertens, employer, CWI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CWI Context triple: [Lambert Meertens, employer, CWI]
-
A.
CWI
chosen
CWI is the Netherlands' national research institute for mathematics and computer science, known for its pioneering contributions to theoretical and applied informatics.
-
B.
KWI
KWI is the three-letter IATA airport code for Kuwait International Airport, the main international gateway to Kuwait.
-
C.
CCIW
CCIW is an NCAA Division III athletic conference composed primarily of private colleges in Illinois and Wisconsin.
-
D.
CWA
CWA is a major U.S. environmental law that regulates the discharge of pollutants into the nation’s waters and sets water quality standards.
-
E.
CWA
CWA is the standard abbreviation for the Chinese Weiqi Association, the national governing body for the board game Go (Weiqi) in China.
- 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_69d6aa8081448190a9324184f2bd1c26 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d734d3eab88190b30a3025b6b2b0bc |
completed | April 9, 2026, 5:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de8592d8f08190ac577395ad7cc557 |
completed | April 14, 2026, 6:21 p.m. |
Created at: April 8, 2026, 9:19 p.m.