Triple
T9921189
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gangapurna |
E187798
|
entity |
| Predicate | photoAppearsIn |
P37258
|
FINISHED |
| Object | views from Manang on Annapurna Circuit |
—
|
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: views from Manang on Annapurna Circuit | Statement: [Gangapurna, photoAppearsIn, views from Manang on Annapurna Circuit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: photoAppearsIn Context triple: [Gangapurna, photoAppearsIn, views from Manang on Annapurna Circuit]
-
A.
imagedIn
chosen
Indicates that one entity appears within or is depicted in an image associated with another entity.
-
B.
photographsTakenIn
Indicates that photographs were captured or taken within a specific location or place.
-
C.
appearsInWorkOfArt
Indicates that an entity is depicted, represented, or otherwise featured within a particular work of art.
-
D.
mediaDepictionAs
Indicates that one entity is portrayed or represented as another entity or in a particular way within some medium (e.g., image, film, text).
-
E.
hasPhotoOn
Indicates that one entity has an associated photograph stored, displayed, or linked on another entity (such as a platform, page, or medium).
- 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_69ca82b22a688190b52c75bd48429c10 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cdb56abbb88190a21b8b77f1a25b81 |
completed | April 2, 2026, 12:16 a.m. |
| PD | Predicate disambiguation | batch_69cd1d90b8a8819081748f129c0c6ab6 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:42 p.m.