Triple
T1142938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gouden Bocht |
E23495
|
entity |
| Predicate | streetAddressRange |
P24400
|
FINISHED |
| Object | Herengracht 368–502 (approximate) |
—
|
LITERAL 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: Herengracht 368–502 (approximate) | Statement: [Gouden Bocht, streetAddressRange, Herengracht 368–502 (approximate)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: streetAddressRange Context triple: [Gouden Bocht, streetAddressRange, Herengracht 368–502 (approximate)]
-
A.
streetAddress
Indicates the specific location of an entity in terms of its numbered building and street name within a postal address.
-
B.
postalCodeRange
Indicates that one entity specifies a contiguous range of postal codes applicable to another entity or context.
-
C.
boroughNumber
Indicates the numerical identifier assigned to a specific borough within a larger administrative or municipal division.
-
D.
addressLength
Indicates the length or number of characters in an address.
-
E.
addresses
Indicates that one entity directs speech, communication, or written correspondence specifically toward another entity.
- F. None of above. chosen
Provenance (4 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_69a493ef399c8190b04b9146d2314f59 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4bc4e93d48190b9fea886bf61aad7 |
completed | March 1, 2026, 10:23 p.m. |
| PD | Predicate disambiguation | batch_69a4bb4d4104819084027a043c6118cb |
completed | March 1, 2026, 10:18 p.m. |
| PDg | Predicate description generation | batch_69a4bbb9fb4c81909dd39c496893c21b |
completed | March 1, 2026, 10:20 p.m. |
Created at: March 1, 2026, 7:44 p.m.