Triple
T27119365
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lord of Marsan |
E686949
|
entity |
| Predicate | hasTerritorialHolding |
P92975
|
FINISHED |
| Object | Marsan |
—
|
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: Marsan | Statement: [Lord of Marsan, hasTerritorialHolding, Marsan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTerritorialHolding Context triple: [Lord of Marsan, hasTerritorialHolding, Marsan]
-
A.
hasTerritorialPossession
chosen
Indicates that one entity holds ownership, control, or legal rights over a specific territory or geographic area.
-
B.
heldTerritory
Indicates that one entity maintained control or possession over a specific territory or geographic area.
-
C.
hasTerritorialInterestIn
Indicates that an entity claims, seeks, or maintains control, influence, or rights over a specific geographic area or territory.
-
D.
hasTerritorialAssociation
Indicates a relationship where an entity is linked or connected to a specific territory, area, or geographic region.
-
E.
hasMajorTerritory
Indicates that one entity possesses or controls the primary geographic area or domain associated with another 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_69ef148c2b588190afc15b529f7af845 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f6d0d46aec819091edf97324d793ac |
completed | May 3, 2026, 4:36 a.m. |
| PD | Predicate disambiguation | batch_69f6cfe2183481908ae4e85a59c66f69 |
completed | May 3, 2026, 4:32 a.m. |
Created at: April 27, 2026, 8:58 a.m.