Triple
T19931759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hourglass Nebula region |
E479069
|
entity |
| Predicate | bestObservedDuring |
P38291
|
FINISHED |
| Object | northern summer months |
—
|
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: northern summer months | Statement: [Hourglass Nebula region, bestObservedDuring, northern summer months]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bestObservedDuring Context triple: [Hourglass Nebula region, bestObservedDuring, northern summer months]
-
A.
bestObservedWith
Indicates that one entity is most effectively or appropriately observed, detected, or measured when used or considered together with another specified entity.
-
B.
observedWhen
chosen
Indicates that one entity is observed or recorded at a specific time or under particular temporal conditions.
-
C.
observedSince
Indicates that one entity has been continuously or repeatedly observed starting from a specified point in time.
-
D.
observedAt
Indicates that an entity was recorded or noticed at a specific time or place.
-
E.
isObservedBestFrom
Indicates that something is most favorably or clearly seen, perceived, or measured from a particular viewpoint, location, or context compared to other alternatives.
- 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_69d8e521855c8190b41871700afc8d6a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65a13ebc08190a583aa4c5e9f6648 |
completed | April 20, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69e537f070b481908958e0e5911dcdc1 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:53 p.m.