Triple
T5202256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Milky Way stellar halo |
E117419
|
entity |
| Predicate | hasExtent |
P20336
|
FINISHED |
| Object | tens of kiloparsecs |
—
|
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: tens of kiloparsecs | Statement: [Milky Way stellar halo, hasExtent, tens of kiloparsecs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasExtent Context triple: [Milky Way stellar halo, hasExtent, tens of kiloparsecs]
-
A.
hasApproximateExtent
chosen
Indicates that one entity has a spatial, temporal, or quantitative extent that is only roughly or approximately specified rather than exact.
-
B.
eezExtent
Indicates the geographic area or spatial coverage of a country's exclusive economic zone (EEZ).
-
C.
hasExpansion
Indicates that one entity serves as a larger, extended, or elaborated form of another entity.
-
D.
supportsExtentBasedAllocation
Indicates that one entity provides or enables allocation of resources based on contiguous extents rather than fixed-size blocks.
-
E.
extendsTo
Indicates that one entity reaches, stretches, or continues its scope, influence, or coverage up to or into another 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_69bd4463dd3c81909966123f20b79d57 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7adb034c819086bf8a85fbf158f4 |
completed | March 20, 2026, 4:50 p.m. |
| PD | Predicate disambiguation | batch_69bd77b9a67c8190819612257ea746b4 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:47 p.m.