Triple
T26555177
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glacial Lake Iroquois |
E671787
|
entity |
| Predicate | shorelineRemnantVisibleAt |
P160635
|
FINISHED |
| Object | Scarborough Bluffs |
—
|
NE NERFINISHED |
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: Scarborough Bluffs | Statement: [Glacial Lake Iroquois, shorelineRemnantVisibleAt, Scarborough Bluffs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shorelineRemnantVisibleAt Context triple: [Glacial Lake Iroquois, shorelineRemnantVisibleAt, Scarborough Bluffs]
-
A.
visibilityFromShore
Indicates that something can be seen or is visually detectable from the shoreline or coast.
-
B.
hasShorelineMarker
Indicates that a location or area is marked or delineated by a designated shoreline indicator or boundary marker.
-
C.
shorelineIncludes
Indicates that a shoreline spatially contains or encompasses a specified coastal feature or segment.
-
D.
visibilityFromSea
Indicates that something can be seen or is visually detectable when viewed from the sea.
-
E.
hasShorelineMaterial
Indicates that a geographic feature’s shoreline is composed of or characterized by a specified material.
- 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_69eeb32163f08190af5f81282738e27a |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f614661bc08190bd533fbfac7da9fe |
completed | May 2, 2026, 3:12 p.m. |
| PD | Predicate disambiguation | batch_69f602d7b1b0819095ddd3b5169f8ce2 |
completed | May 2, 2026, 1:57 p.m. |
| PDg | Predicate description generation | batch_69f6037bf7a081908862a8359be80cf8 |
completed | May 2, 2026, 2 p.m. |
Created at: April 27, 2026, 1:49 a.m.