Triple
T3724024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Varuna |
E81704
|
entity |
| Predicate | likelyComposition |
P51231
|
FINISHED |
| Object | mixture of ice and rock |
—
|
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: mixture of ice and rock | Statement: [Varuna, likelyComposition, mixture of ice and rock]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: likelyComposition Context triple: [Varuna, likelyComposition, mixture of ice and rock]
-
A.
specialComposition
Indicates that one entity is composed of another in a distinctive or non-standard way, highlighting a particular or exceptional form of composition between them.
-
B.
composedIn
Indicates that a creative work was written or musically composed within a particular place or during a specific time period.
-
C.
possiblePlaceOfComposition
Indicates that a location is a plausible or hypothesized place where a work was composed.
-
D.
definesComposition
Indicates that one entity specifies or establishes the structural or component makeup of another entity.
-
E.
possibleRelative
Indicates a relationship where one entity may be related to another by family or kinship, but the exact nature of the relationship is uncertain or not fully established.
- 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_69ad8b1b7ef081908d2d381bbf54985a |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcaf3f2ec8190a3a8f363cfb762f3 |
completed | March 8, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_69adc0452f5081909c79e114a86cce8c |
completed | March 8, 2026, 6:30 p.m. |
| PDg | Predicate description generation | batch_69adc226fffc81909c679b44e611fee6 |
completed | March 8, 2026, 6:38 p.m. |
Created at: March 8, 2026, 3:34 p.m.