Triple
T38173426
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fritz Pfeffer's room |
E1000138
|
entity |
| Predicate | belongsToBuilding |
P202106
|
FINISHED |
| Object | canal house at Prinsengracht 263 |
—
|
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: canal house at Prinsengracht 263 | Statement: [Fritz Pfeffer's room, belongsToBuilding, canal house at Prinsengracht 263]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: belongsToBuilding Context triple: [Fritz Pfeffer's room, belongsToBuilding, canal house at Prinsengracht 263]
-
A.
belongsToBuildingType
Indicates that something is classified as being of a particular building type.
-
B.
belongsToBuildingComplex
Indicates that one building or structure is part of, or included within, a larger building complex.
-
C.
refersToBuildingOn
Indicates that one entity explicitly references or designates a specific building as its subject or target.
-
D.
containsBuilding
Indicates that one location or area includes a building within its boundaries.
-
E.
appliedToBuilding
Indicates that something (such as a process, treatment, regulation, or attribute) is directed toward, implemented on, or otherwise affects a building.
- 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_69f76daaace48190a38cee37f8ce343f |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a00512437d48190ad20324968ead5f4 |
completed | May 10, 2026, 9:34 a.m. |
| PD | Predicate disambiguation | batch_6a0050227350819099f41369c3d168be |
completed | May 10, 2026, 9:30 a.m. |
| PDg | Predicate description generation | batch_6a0051234cc08190adae6e2cfae2f8cc |
completed | May 10, 2026, 9:34 a.m. |
Created at: May 3, 2026, 4:29 p.m.