Triple
T22701338
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kerta Gosa Pavilion |
E561330
|
entity |
| Predicate | languageOfInscriptions |
P5668
|
FINISHED |
| Object | Kawi |
—
|
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: Kawi | Statement: [Kerta Gosa Pavilion, languageOfInscriptions, Kawi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kawi Context triple: [Kerta Gosa Pavilion, languageOfInscriptions, Kawi]
-
A.
Kawi
Kawi is an ancient Brahmic script historically used in maritime Southeast Asia, particularly for Old Javanese and related languages.
-
B.
Teika
Teika is the commonly used name for Fujiwara no Teika, a renowned Japanese poet, critic, and anthologist of the late Heian and early Kamakura periods.
-
C.
Man'yōgana
Man'yōgana is an ancient Japanese writing system that used Chinese characters phonetically and served as a precursor to the modern hiragana and katakana syllabaries.
-
D.
Kawi language
chosen
Kawi language is an Old Javanese literary and liturgical language of ancient Indonesia, historically used in inscriptions and classical texts across the region.
-
E.
Akananuru
Akananuru is a classical Tamil poetic anthology of 400 love-themed poems that forms a key part of the ancient Sangam literature.
- 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_69e2454e615481909c177440be559d2c |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f178cb2f548190bfc6f050be7c795a |
completed | April 29, 2026, 3:19 a.m. |
Created at: April 17, 2026, 3:15 p.m.