Triple
T19260685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Milky Way dark matter halo |
E481640
|
entity |
| Predicate | hasVirialMass |
P135105
|
FINISHED |
| Object | approximately 0.5–2 × 10^12 solar masses |
—
|
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: approximately 0.5–2 × 10^12 solar masses | Statement: [Milky Way dark matter halo, hasVirialMass, approximately 0.5–2 × 10^12 solar masses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasVirialMass Context triple: [Milky Way dark matter halo, hasVirialMass, approximately 0.5–2 × 10^12 solar masses]
-
A.
isGravitationallyBound
Indicates that one object is held in a stable or semi-stable configuration by the gravitational attraction of another (or others), such that it cannot escape without additional energy.
-
B.
hasDarkMatterHalo
Indicates that an astronomical object is surrounded by or associated with a dark matter halo.
-
C.
hasGasMass
Indicates that an entity possesses a specified amount of gas mass as one of its physical properties.
-
D.
hasStellarMassClass
Indicates the classification relationship that assigns an object to a specific category based on its stellar mass.
-
E.
hasRadialVelocityDispersion
Indicates that an entity exhibits a spread in its radial velocities, quantifying how much the line-of-sight speeds of its components differ from one another.
- 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_69d8e8ce54cc8190998418ff1f66ef28 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fb890e7c8190beba407f63459382 |
completed | April 20, 2026, 10:10 a.m. |
| PD | Predicate disambiguation | batch_69e4dd002d00819088b625056edfb74e |
completed | April 19, 2026, 1:47 p.m. |
| PDg | Predicate description generation | batch_69e4ddcf50108190a09d0f1291c17374 |
completed | April 19, 2026, 1:51 p.m. |
Created at: April 10, 2026, 1:28 p.m.