Triple
T9638837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gniezno Land |
E233005
|
entity |
| Predicate | earlyPoliticalCenterOf |
P4099
|
FINISHED |
| Object | Polish state |
—
|
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: Polish state | Statement: [Gniezno Land, earlyPoliticalCenterOf, Polish state]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: earlyPoliticalCenterOf Context triple: [Gniezno Land, earlyPoliticalCenterOf, Polish state]
-
A.
ancientPolisCenter
Indicates that a location functioned as the central urban, political, or social hub of an ancient polis (city-state).
-
B.
hasMajorHistoricalCentersIn
Indicates that an entity possesses significant, historically important centers or hubs located within a specified place or region.
-
C.
earliestUnificationCenter
Indicates the location that served as the first or primary center where separate entities were brought together into a unified whole.
-
D.
isDiplomaticCenterOf
Indicates that a location serves as the primary site or hub for conducting diplomatic activities and relations for a specified entity.
-
E.
wasFirstCapitalOf
chosen
Indicates that one place previously served as the earliest or original capital city of another political or administrative entity.
- 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_69ca848a5a908190aad251f4137b0c3a |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9b532aa4819087b56be6f5635126 |
completed | April 1, 2026, 10:25 p.m. |
| PD | Predicate disambiguation | batch_69ccd5acfa5c8190aaba3cf548723604 |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:11 p.m.