Triple
T36082958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roosevelt Island Climate Evolution (RICE) project |
E1043699
|
entity |
| Predicate | hasStudyRegion |
P37341
|
FINISHED |
| Object | Ross Ice Shelf sector |
—
|
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: Ross Ice Shelf sector | Statement: [Roosevelt Island Climate Evolution (RICE) project, hasStudyRegion, Ross Ice Shelf sector]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStudyRegion Context triple: [Roosevelt Island Climate Evolution (RICE) project, hasStudyRegion, Ross Ice Shelf sector]
-
A.
studiesRegion
chosen
Indicates that an entity engages in the academic or systematic study of a particular geographic or cultural region.
-
B.
hasStudyAreas
Indicates that an entity includes, encompasses, or is associated with one or more specific areas of study.
-
C.
hasStudyAreaType
Indicates that an entity’s study area is classified as a specific type or category (e.g., lab, field site, classroom).
-
D.
studiedInRegion
Indicates that an entity pursued studies or received education within a specified geographic region.
-
E.
hasRegion
Indicates that an entity includes, contains, or is associated with a specific geographic or administrative region as part of its scope or structure.
- 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_69f76e3154908190a6f702671c2bea08 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a002962f6e081909906d6436bae6407 |
completed | May 10, 2026, 6:44 a.m. |
| PD | Predicate disambiguation | batch_6a00284c9c7c8190a77f18a41eee55df |
completed | May 10, 2026, 6:40 a.m. |
Created at: May 3, 2026, 4:08 p.m.