Triple
T2985474
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fanny Blankers-Koen |
E80614
|
entity |
| Predicate | placeOfBirth |
P1
|
FINISHED |
| Object | Hoofddorp |
E76459
|
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: Hoofddorp | Statement: [Fanny Blankers-Koen, placeOfBirth, Hoofddorp]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hoofddorp Context triple: [Fanny Blankers-Koen, placeOfBirth, Hoofddorp]
-
A.
Hoofddorp
chosen
Hoofddorp is the main town and administrative center of the municipality of Haarlemmermeer in the Netherlands.
-
B.
Zoetermeer
Zoetermeer is a modern, rapidly grown satellite city of The Hague in the western Netherlands, known for its residential neighborhoods and light-rail connections.
-
C.
Leidschendam-Voorburg
Leidschendam-Voorburg is a municipality in the western Netherlands, near The Hague, formed by the towns of Leidschendam and Voorburg.
-
D.
Houten
Houten is a Dutch town in the province of Utrecht, known for its bicycle-friendly urban design and as the home of the Royal Dutch Mint.
-
E.
Zoeterwoude
Zoeterwoude is a small Dutch municipality and village known for its rural character and location near Leiden in the province of South Holland.
- 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_69ad8b16c3488190b47b6aa7a59a335b |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad99c65ad0819087bb4ae92ab0dc55 |
completed | March 8, 2026, 3:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c9251db3388190b8b0ac7549647887 |
completed | March 29, 2026, 1:11 p.m. |
Created at: March 8, 2026, 2:59 p.m.