Triple
T14231056
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Javanese Hindu-Buddhist civilization |
E352749
|
entity |
| Predicate | capitalCities |
P100362
|
FINISHED |
| Object | Trowulan |
E71241
|
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: Trowulan | Statement: [Javanese Hindu-Buddhist civilization, capitalCities, Trowulan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Trowulan Context triple: [Javanese Hindu-Buddhist civilization, capitalCities, Trowulan]
-
A.
Trowulan
chosen
Trowulan is an archaeological site in East Java, Indonesia, believed to be the former royal city and cultural center of the Majapahit Empire.
-
B.
Tahara
Tahara is a coastal city in central Japan known for its automotive manufacturing industry and scenic Cape Irago on the Atsumi Peninsula.
-
C.
Tahara
Tahara is a feminine given name, often considered a variant of Tara, used in various cultures.
-
D.
Seibal
Seibal is an ancient Maya archaeological site in Guatemala known for its well-preserved stelae and strategic location along the Usumacinta River.
-
E.
Chanhu-daro
Chanhu-daro is an archaeological site of the Indus Valley Civilization in present-day Pakistan, notable for its urban planning, craft production, and evidence of early writing.
- 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_69d8278adc7c8190a9218d69bce3c4e6 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de622b89fc8190af08dab9e1976759 |
completed | April 14, 2026, 3:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd3251ec5881909fcebc9477d6a761 |
completed | May 8, 2026, 12:46 a.m. |
Created at: April 10, 2026, 1:07 a.m.