Triple
T21293663
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Devenish Island |
E524858
|
entity |
| Predicate | roundTowerEntranceHeight |
P89649
|
FINISHED |
| Object | about 3.6 metres above ground |
—
|
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: about 3.6 metres above ground | Statement: [Devenish Island, roundTowerEntranceHeight, about 3.6 metres above ground]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roundTowerEntranceHeight Context triple: [Devenish Island, roundTowerEntranceHeight, about 3.6 metres above ground]
-
A.
entranceHeight
chosen
Indicates the vertical measurement of how tall an entrance is.
-
B.
towerAccessibleTo
Indicates that a particular tower can be reached, entered, or used by a specified agent or group under given conditions.
-
C.
entranceSize
Indicates the size or dimensions of an entrance relative to a referenced object or structure.
-
D.
hasEntranceElevation
Indicates the elevation at which an entity’s entrance is located, typically measured relative to a reference level such as sea level or ground level.
-
E.
towerAccessibleBy
Indicates that a tower can be reached or entered via a specified route, path, or means of access.
- 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_69e0b517e6748190850d6f6ddf323d69 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e73856ba988190a8359efecea362cc |
completed | April 21, 2026, 8:41 a.m. |
| PD | Predicate disambiguation | batch_69e61612ab748190a72b8703b938abcb |
completed | April 20, 2026, 12:03 p.m. |
Created at: April 16, 2026, 4:04 p.m.