Triple
T18014947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hezhou |
E430976
|
entity |
| Predicate | borders |
P224
|
FINISHED |
| Object | Laibin |
—
|
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: Laibin | Statement: [Hezhou, borders, Laibin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Laibin Context triple: [Hezhou, borders, Laibin]
-
A.
Laibin
chosen
Laibin is a prefecture-level city in south-central China known for its role as a regional transportation hub and its mix of industrial and agricultural development.
-
B.
Lubja
Lubja is a small village located within Viimsi Parish in northern Estonia, near the capital city of Tallinn.
-
C.
Licinia
Licinia was a Roman noblewoman of the late Republic, known primarily as the daughter of Mucia Tertia and thus connected to prominent political families of her time.
-
D.
Ludza
Ludza is one of the principal towns of the Latgale region in eastern Latvia, known for its historic castle ruins and status as one of the country’s oldest settlements.
-
E.
Libo
Libo is an ancient Roman cognomen associated with members of the patrician Julii family.
- 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_69d8b904530081908bf341d842464856 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4b522e84c8190a03f6445df9f5ac8 |
completed | April 19, 2026, 10:57 a.m. |
Created at: April 10, 2026, 10:24 a.m.