Triple
T26179824
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary of Savoy |
E654642
|
entity |
| Predicate | hasFamilyInfluenceRegion |
P114304
|
FINISHED |
| Object | Northern Italy |
—
|
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: Northern Italy | Statement: [Mary of Savoy, hasFamilyInfluenceRegion, Northern Italy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFamilyInfluenceRegion Context triple: [Mary of Savoy, hasFamilyInfluenceRegion, Northern Italy]
-
A.
familyInfluenceArea
chosen
Indicates the domain or scope within which a family exerts influence, impact, or control over something or someone.
-
B.
influencesRegion
Indicates that one entity has an effect on, shapes, or alters the conditions, characteristics, or behavior of a specified region.
-
C.
hasFamilyBackgroundIn
Indicates that an entity comes from, or is associated with, a particular familial or ancestral background.
-
D.
hasRegionalInfluenceFrom
Indicates that one entity’s influence, impact, or authority in a region is derived from or shaped by another entity.
-
E.
hasExternalInfluence
Indicates that one entity affects or alters another entity due to factors or forces originating outside the affected 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_69ee5b45873c81909499203612d05d07 |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f676c440708190a4b9974e95d2291a |
completed | May 2, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69f675fd59608190b246383435e68fce |
completed | May 2, 2026, 10:09 p.m. |
Created at: April 26, 2026, 8:39 p.m.