Triple
T11518288
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ji'an |
E273087
|
entity |
| Predicate | locatedInProvinceCapitalDirection |
P84796
|
FINISHED |
| Object | south of Nanchang |
—
|
LITERAL 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: south of Nanchang | Statement: [Ji'an, locatedInProvinceCapitalDirection, south of Nanchang]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedInProvinceCapitalDirection Context triple: [Ji'an, locatedInProvinceCapitalDirection, south of Nanchang]
-
A.
locatedInCountryCapitalOfProvince
Indicates that an entity is located in the country that contains the capital city of a specified province.
-
B.
stateCapitalDirectionFrom
chosen
Indicates the cardinal or relative direction of a state’s capital city from a specified reference location.
-
C.
capitalOfProvinceNearby
Indicates that a city serves as the capital of a province that is geographically close to a specified reference location or area.
-
D.
adjacentToProvinceCapital
Indicates that a location is directly next to or bordering the capital city of a province.
-
E.
servesProvinceCapital
Indicates that a city functions as the administrative or service center for a given province’s capital.
- F. None of above.
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_69d6aae2c3748190bed2ea50dfb160dc |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d87fcf927081908ef89eff7ad833b0 |
completed | April 10, 2026, 4:42 a.m. |
| PD | Predicate disambiguation | batch_69d80876e5f0819088cff2e72f773cf6 |
completed | April 9, 2026, 8:13 p.m. |
Created at: April 8, 2026, 9:36 p.m.