Triple
T20480393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GD-1 stream |
E502434
|
entity |
| Predicate | isUsedToConstrain |
P49586
|
FINISHED |
| Object | Milky Way mass distribution |
—
|
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: Milky Way mass distribution | Statement: [GD-1 stream, isUsedToConstrain, Milky Way mass distribution]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isUsedToConstrain Context triple: [GD-1 stream, isUsedToConstrain, Milky Way mass distribution]
-
A.
designedToConstrain
chosen
Indicates that one entity is intentionally created or configured to limit, restrict, or control the behavior, range, or properties of another entity.
-
B.
constrainedBy
Indicates that one entity’s state, behavior, or possibilities are limited, restricted, or governed by another entity.
-
C.
usesRestraints
Indicates that one entity applies or employs physical or procedural restraints on another entity.
-
D.
usesConstriction
Indicates that one entity applies pressure by tightening or squeezing around another entity to restrain, control, or affect it.
-
E.
hasFormalConstraint
Indicates that an entity is governed or restricted by an explicitly defined formal rule, condition, or limitation.
- 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_69e0b4af32848190aea80682b44d5d6e |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69b55d7a881909dfe3ea0e74b742b |
completed | April 20, 2026, 9:32 p.m. |
| PD | Predicate disambiguation | batch_69e59fcdf6e08190a604204615dc56e6 |
completed | April 20, 2026, 3:38 a.m. |
Created at: April 16, 2026, 11:34 a.m.