Triple
T4885974
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Perseus molecular cloud complex |
E109439
|
entity |
| Predicate | hasPhysicalSize |
P18961
|
FINISHED |
| Object | tens of parsecs |
—
|
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 parsecs | Statement: [Perseus molecular cloud complex, hasPhysicalSize, tens of parsecs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPhysicalSize Context triple: [Perseus molecular cloud complex, hasPhysicalSize, tens of parsecs]
-
A.
hasPhysicalFootprint
Indicates that one entity occupies or affects a specific physical area or space in the real world.
-
B.
hasPhysicalMedium
Indicates that one entity serves as the tangible carrier or material form through which another entity exists, is stored, or is transmitted.
-
C.
hasDimensionsApprox
chosen
Indicates that an entity has physical dimensions that are known only approximately, rather than as exact measurements.
-
D.
modelSize
Indicates the quantitative measure of how large or complex a model is, typically in terms of parameters, layers, or memory footprint.
-
E.
bodySize
Indicates the relative physical magnitude or scale of an entity’s body, such as how large or small it is.
- 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_69bd440f71348190b99938e59fb7f9a1 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6e01872c81909607010c10538ad1 |
completed | March 20, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69bd6c2be5e881909f6ec9c3bcde49f3 |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:28 p.m.