Triple
T26321814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | VLBA antenna at Brewster, Washington |
E662132
|
entity |
| Predicate | arrayRole |
P90497
|
FINISHED |
| Object |
VLBA western U.S. station
The VLBA western U.S. station is a Very Long Baseline Array radio telescope facility located in Brewster, Washington, that contributes to high-resolution astronomical observations.
|
E662132
|
NE FINISHED |
How this triple was built (3 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: VLBA western U.S. station | Statement: [VLBA antenna at Brewster, Washington, arrayRole, VLBA western U.S. station]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: VLBA western U.S. station Triple: [VLBA antenna at Brewster, Washington, arrayRole, VLBA western U.S. station]
Generated description
The VLBA western U.S. station is a Very Long Baseline Array radio telescope facility located in Brewster, Washington, that contributes to high-resolution astronomical observations.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: arrayRole Context triple: [VLBA antenna at Brewster, Washington, arrayRole, VLBA western U.S. station]
-
A.
authorityRole
Indicates that one entity holds an official position or role that grants it authority or control over another entity or within a specific context.
-
B.
airGroupRole
Indicates the specific function or duty an air group performs within a larger operation or organizational context.
-
C.
antRole
chosen
Indicates that one entity has a specific role, function, or responsibility in relation to another entity.
-
D.
libraryRole
Indicates the specific function, responsibility, or position an entity holds within the context of a library.
-
E.
massRole
Indicates that an entity plays a specific role or function within a mass or collective context.
- F. None of above.
Provenance (6 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_69ee812e73048190aae587f1d51e5a06 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f60f2bce2881909a81127b9824b3cd |
completed | May 2, 2026, 2:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a118fda34a48190a6c27d548e50f959 |
completed | May 23, 2026, 11:30 a.m. |
| NEDg | Description generation | batch_6a119071f348819093c113dab0fcea45 |
completed | May 23, 2026, 11:33 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a1190efe1a8819097407e675292a7e4 |
completed | May 23, 2026, 11:35 a.m. |
| PD | Predicate disambiguation | batch_69f5f7ff548c8190a23e98c5e66e0bc7 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 10:28 p.m.