Triple
T31183367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gisulf II of Friuli |
E794963
|
entity |
| Predicate | realmBordered |
P171226
|
FINISHED |
| Object | Byzantine territories in northeastern Italy |
—
|
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: Byzantine territories in northeastern Italy | Statement: [Gisulf II of Friuli, realmBordered, Byzantine territories in northeastern Italy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: realmBordered Context triple: [Gisulf II of Friuli, realmBordered, Byzantine territories in northeastern Italy]
-
A.
borderWithin
Indicates that one region’s border lies entirely inside the boundary of another region.
-
B.
realmWithin
Indicates that one realm or domain is contained inside, or exists as a subset of, another realm or domain.
-
C.
guardedBorderWith
Indicates a relationship where a shared border between two entities is actively protected or monitored, typically for security or control purposes.
-
D.
borderArea
Indicates that an area lies along or near the boundary between two regions, countries, or territories.
-
E.
realmRuled
Indicates that one entity serves as the sovereign or governing ruler over a particular realm, territory, or domain.
- F. None of above. chosen
Provenance (4 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_69f224d675d08190957198068e440422 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69c6f01e881908fa84f5d429d37ae |
completed | May 3, 2026, 12:53 a.m. |
| PD | Predicate disambiguation | batch_69f69665cd9c819088c388fc82fec42e |
completed | May 3, 2026, 12:27 a.m. |
| PDg | Predicate description generation | batch_69f69c2127088190ae92c72461576d3b |
completed | May 3, 2026, 12:51 a.m. |
Created at: April 29, 2026, 9:08 p.m.