Triple
T12103645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A-Group |
E288247
|
entity |
| Predicate | hasTypeSite |
P44791
|
FINISHED |
| Object | Ballana |
E66782
|
NE 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: Ballana | Statement: [A-Group, hasTypeSite, Ballana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ballana Context triple: [A-Group, hasTypeSite, Ballana]
-
A.
Ballana
chosen
Ballana is an important archaeological site in Lower Nubia known for its rich group of royal tumulus graves from the post-Meroitic period.
-
B.
Baniata
Baniata is an Oceanic language of the Meso-Melanesian group spoken in the Solomon Islands.
-
C.
Barshaini
Barshaini is a small Himalayan village in Himachal Pradesh, India, that serves as a popular base and trailhead for treks into the Parvati Valley and surrounding high-altitude landscapes.
-
D.
Balya
Balya is a small town and district in western Turkey known historically for its mining activities and rural character.
-
E.
Bala
Bala is a small historic market town in Gwynedd, Wales, best known for its proximity to Llyn Tegid (Bala Lake), the largest natural lake in Wales.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6ab4a5c448190a110d1273314b21a |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d915568b9881909fc9edacefb86409 |
completed | April 10, 2026, 3:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f5f677039481908f14fa12b9b86910 |
completed | May 2, 2026, 1:04 p.m. |
Created at: April 8, 2026, 9:48 p.m.