Triple
T8398902
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shangri-La dune fields on Titan |
E198121
|
entity |
| Predicate | hasPrimaryConstituent |
P82021
|
FINISHED |
| Object | hydrocarbon particles |
—
|
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: hydrocarbon particles | Statement: [Shangri-La dune fields on Titan, hasPrimaryConstituent, hydrocarbon particles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryConstituent Context triple: [Shangri-La dune fields on Titan, hasPrimaryConstituent, hydrocarbon particles]
-
A.
hasPrimarySubject
Indicates that an entity is the main or principal subject associated with another entity or resource.
-
B.
hasPrimaryFeature
Indicates that an entity possesses a main or most characteristic feature that defines or distinguishes it.
-
C.
hasPrimarySee
Indicates that one entity is designated as the main or preferred "see" reference or cross-reference for another entity.
-
D.
hasPrimaryFunction
Indicates that one entity serves as the main or principal function or role of another entity.
-
E.
hasPrimaryCode
Indicates that an entity is associated with its main or most important identifying code among potentially multiple codes.
- 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_69ca82f816bc8190ab321c07d72208c1 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb824ac29481909f02cdb2b7cd18af |
completed | March 31, 2026, 8:14 a.m. |
| PD | Predicate disambiguation | batch_69cb70d24b248190a326aa6804f942b5 |
completed | March 31, 2026, 6:59 a.m. |
| PDg | Predicate description generation | batch_69cb77690720819099de1e22b84a9563 |
completed | March 31, 2026, 7:27 a.m. |
Created at: March 30, 2026, 6:04 p.m.