Triple
T38582867
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frozen Sea |
E932283
|
entity |
| Predicate | secondaryElement |
P28553
|
FINISHED |
| Object | ice |
—
|
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: ice | Statement: [Frozen Sea, secondaryElement, ice]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondaryElement Context triple: [Frozen Sea, secondaryElement, ice]
-
A.
secondElement
Indicates that one entity is the second element in an ordered pair, sequence, or collection relative to another entity.
-
B.
secondaryTo
Indicates that one condition, event, or factor occurs as a consequence of, or is caused by, another primary condition, event, or factor.
-
C.
secondaryConstituent
chosen
Indicates that one entity functions as a secondary or subordinate component, element, or member within the structure or composition of another entity.
-
D.
secondarySurface
Indicates a relationship where one surface functions as a secondary or subordinate surface in relation to a primary or main surface.
-
E.
secondarySingle
Indicates that an entity serves as a secondary, but singular, counterpart or role in relation to another primary 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ffe23081408190a121d901dbce1403 |
completed | May 10, 2026, 1:41 a.m. |
| PD | Predicate disambiguation | batch_69ffe18aed348190912a5996b2da728b |
completed | May 10, 2026, 1:38 a.m. |
Created at: May 3, 2026, 4:32 p.m.