Triple
T18024277
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bakong |
E431205
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | Roluos Group |
—
|
NE NERFINISHED |
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: Roluos Group | Statement: [Bakong, partOf, Roluos Group]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roluos Group Context triple: [Bakong, partOf, Roluos Group]
-
A.
Roluos Group
chosen
The Roluos Group is a cluster of early Angkor-era temple complexes near Siem Reap in Cambodia, notable for marking the beginnings of classical Khmer temple architecture.
-
B.
Rokkaku Group
The Rokkaku Group is a powerful, authoritarian corporation and crime syndicate that serves as the main villainous organization opposing the player’s graffiti gang in the Jet Set Radio video game series.
-
C.
Aunus Group
The Aunus Group was a Finnish military formation that operated on the eastern front during World War II, particularly in the region of East Karelia.
-
D.
Lihir Group
Lihir Group is a volcanic island group in Papua New Guinea known for its large gold deposits and the major Lihir Gold Mine.
-
E.
Emperor Group
Emperor Group is a Hong Kong-based conglomerate with diversified interests spanning entertainment, property, financial services, and retail.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9050fb48190890155145deb0a66 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4b9c475dc819086c4cd86d663791f |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 10:24 a.m.