Triple
T17666501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Double Island Point |
E440396
|
entity |
| Predicate | lighthouseConstruction |
P75863
|
FINISHED |
| Object | timber-framed tower |
—
|
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: timber-framed tower | Statement: [Double Island Point, lighthouseConstruction, timber-framed tower]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lighthouseConstruction Context triple: [Double Island Point, lighthouseConstruction, timber-framed tower]
-
A.
lighthouseConstructedIn
Indicates that a lighthouse was built or established during a specific time period or in a specific year.
-
B.
lighthouseConstructionMaterial
chosen
Indicates the material from which a lighthouse is built or primarily constructed.
-
C.
lighthouseHeight
Indicates the vertical measurement of a lighthouse from its base to its top.
-
D.
lighthouseName
Indicates that a lighthouse is identified by a specific name.
-
E.
lighthouseFunction
Indicates that an entity serves as a lighthouse, providing navigational guidance or warning signals to other entities (such as ships or aircraft).
- 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_69d8b9e87e18819087104a44dc4dc5b1 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e46ea9d91c81908414ef38c7fb36a4 |
completed | April 19, 2026, 5:56 a.m. |
| PD | Predicate disambiguation | batch_69e3cde007d8819090dd92eea9f022cc |
completed | April 18, 2026, 6:30 p.m. |
Created at: April 10, 2026, 9:57 a.m.