Triple
T36753881
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | House of Savoy |
E907989
|
entity |
| Predicate | countryHistoricallyRuled |
P3022
|
FINISHED |
| Object | Kingdom of Italy |
E11935
|
NE 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: Kingdom of Italy | Statement: [House of Savoy, countryHistoricallyRuled, Kingdom of Italy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryHistoricallyRuled Context triple: [House of Savoy, countryHistoricallyRuled, Kingdom of Italy]
-
A.
countryRuled
chosen
Indicates that one entity exercises governing authority or political control over a country.
-
B.
historicalRegionGoverned
Indicates that a subject entity exercised governing authority over a particular historical region during a specified period.
-
C.
historicallyUnderRuleOf
Indicates that one entity was historically governed, controlled, or ruled by another entity during a past period.
-
D.
administrativeAreaRuled
Indicates that a governing entity holds official administrative authority over a specific geographic area or jurisdiction.
-
E.
capitalOfHistoricalRule
Indicates that one place served as the capital city or seat of government for another entity during a specific historical period of its rule.
- F. None of above.
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_69f76e779bec8190be0e1f87a131e0f4 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a03213d35788190bdf04e19625b4060 |
completed | May 12, 2026, 12:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3dfac86f388190a7c1d09be88b0ee5 |
completed | June 26, 2026, 4:06 a.m. |
| PD | Predicate disambiguation | batch_6a031ea131d48190ab0fecb48b8e2205 |
completed | May 12, 2026, 12:35 p.m. |
Created at: May 3, 2026, 4:12 p.m.