Triple
T9531489
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nubble Light |
E229906
|
entity |
| Predicate | keeperHouseStyle |
P88566
|
FINISHED |
| Object | Victorian-style dwelling |
—
|
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: Victorian-style dwelling | Statement: [Nubble Light, keeperHouseStyle, Victorian-style dwelling]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keeperHouseStyle Context triple: [Nubble Light, keeperHouseStyle, Victorian-style dwelling]
-
A.
countryHouseType
Indicates the type or category of house associated with or characteristic of a particular country.
-
B.
typicalHouse
Indicates that something is a standard or representative example of a house in terms of its usual features, structure, or characteristics.
-
C.
usesHouseStyle
Indicates that one entity follows or applies the specific house style (a defined set of stylistic or formatting conventions) associated with another entity.
-
D.
houses
Indicates that one entity serves as a dwelling or shelter for another entity.
-
E.
traditionalHomeOf
Indicates that a place is historically or customarily regarded as the primary homeland or origin location of a particular group or culture.
- 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_69ca8479934c81908006d0e6e970ae05 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd98b408648190a04127c1d47fe7d2 |
completed | April 1, 2026, 10:14 p.m. |
| PD | Predicate disambiguation | batch_69cca56c44f88190a54a5d2a133bb07e |
completed | April 1, 2026, 4:56 a.m. |
| PDg | Predicate description generation | batch_69cca89f1d748190bf3636bea28d8a37 |
completed | April 1, 2026, 5:09 a.m. |
Created at: March 30, 2026, 8 p.m.