Triple
T19698843
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anga |
E473037
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Champā |
—
|
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: Champā | Statement: [Anga, capital, Champā]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Champā Context triple: [Anga, capital, Champā]
-
A.
Champa
chosen
Champa was an ancient maritime kingdom in what is now central and southern Vietnam, known for its seafaring trade networks, Hindu-Buddhist culture, and distinctive temple architecture.
-
B.
Nag Champa
Nag Champa is a popular aromatic blend, often used in incense and oils, known for its sweet, earthy, and floral fragrance associated with meditation and spiritual practices.
-
C.
Kambos
Kambos is a coastal village on the Greek island of Patmos, known for its sandy beach and role as a popular summer resort area.
-
D.
Khatai
Khatai was the poetic pen name of Shah Ismail I, the founder of the Safavid dynasty and an influential Azerbaijani-Turkic poet.
-
E.
Manipura
Manipura is an ancient kingdom in the Indian epic Mahabharata, known as the realm ruled by Babruvahana, the son of Arjuna.
- 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_69d8e515bef88190bc30781aea50537a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e642b426608190a46abec3652a6ca0 |
completed | April 20, 2026, 3:13 p.m. |
Created at: April 10, 2026, 1:46 p.m.