Triple
T20630748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Holland House ruins |
E506945
|
entity |
| Predicate | originalBuildingCompletedIn |
P12341
|
FINISHED |
| Object | c. 1612 |
—
|
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: c. 1612 | Statement: [Holland House ruins, originalBuildingCompletedIn, c. 1612]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalBuildingCompletedIn Context triple: [Holland House ruins, originalBuildingCompletedIn, c. 1612]
-
A.
originalBuildingConstructed
chosen
Indicates that a particular building was initially constructed in its original form or configuration.
-
B.
predecessorBuildingDate
Indicates that one building’s construction date precedes that of another building in a temporal sequence.
-
C.
locatedInBuildingCompletedIn
Indicates that something is situated within a building that was completed in a specific year or time period.
-
D.
associatedBuildingDate
Indicates the date on which a particular building is formally linked or related to another entity or record.
-
E.
originalBuilding
Indicates that a building is the initial or first version from which later buildings, modifications, or replacements are derived.
- F. None of above.
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_69e0b4bd4a0081908d4e97a590a33fb2 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6ad09c71881909698d3c2576cc181 |
completed | April 20, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69e5a0155bd48190b3c769a12cc2c83d |
completed | April 20, 2026, 3:40 a.m. |
Created at: April 16, 2026, 11:42 a.m.