Triple
T36082963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roosevelt Island Climate Evolution (RICE) project |
E1043699
|
entity |
| Predicate | typeOfCore |
P18973
|
FINISHED |
| Object | deep ice core |
—
|
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: deep ice core | Statement: [Roosevelt Island Climate Evolution (RICE) project, typeOfCore, deep ice core]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfCore Context triple: [Roosevelt Island Climate Evolution (RICE) project, typeOfCore, deep ice core]
-
A.
typicalCoreType
chosen
Indicates that something is a standard or characteristic core type within a given classification or system.
-
B.
executionCoreType
Indicates the specific type or category of execution core (e.g., processing unit or engine) responsible for carrying out a given operation or task.
-
C.
coreUnitType
Indicates that one entity is classified as the primary or fundamental type/category to which another entity (a core unit) belongs.
-
D.
primaryKernelType
Indicates that one entity is the main or default kernel type associated with another entity.
-
E.
coreBasedOn
Indicates that one entity is fundamentally derived from, built upon, or primarily based on another entity.
- 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_6a0235be932081908857bc3a77c27e7d |
completed | May 11, 2026, 8:02 p.m. |
| PD | Predicate disambiguation | batch_6a022c865dec81909e02b2f330e987e6 |
completed | May 11, 2026, 7:22 p.m. |
Created at: May 3, 2026, 4:08 p.m.