Triple
T19713933
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | State of Wu |
E473424
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Gusu |
—
|
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: Gusu | Statement: [State of Wu, capital, Gusu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gusu Context triple: [State of Wu, capital, Gusu]
-
A.
Gusu
chosen
Gusu is an ancient name for the city of Suzhou, historically renowned as a cultural and economic center famed for its classical gardens, canals, and silk.
-
B.
Pojulu
Pojulu are an ethnic group of South Sudan, primarily inhabiting parts of Central Equatoria and speaking a Bari-related Nilotic language.
-
C.
Guzana
Guzana was an important ancient city in the Syro-Anatolian cultural sphere, known as a regional political and administrative center in the early first millennium BCE.
-
D.
Gupis
Gupis is a village and scenic valley area in the Ghizer District of Gilgit-Baltistan, Pakistan, known for its mountainous landscapes and proximity to the Gilgit River.
-
E.
Waras
Waras is a significant town in Afghanistan’s central highland region of Hazarajat, serving as an important local hub for the surrounding Hazara communities.
- 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_69d8e516dd048190a0b6c93ea3e71f58 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6440b47508190a8a33325b00841dc |
completed | April 20, 2026, 3:19 p.m. |
Created at: April 10, 2026, 1:46 p.m.