Triple
T15334502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Margi people |
E366626
|
entity |
| Predicate | primaryResidencePattern |
P6740
|
FINISHED |
| Object | patrilocal residence |
—
|
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: patrilocal residence | Statement: [Margi people, primaryResidencePattern, patrilocal residence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryResidencePattern Context triple: [Margi people, primaryResidencePattern, patrilocal residence]
-
A.
residencyPattern
chosen
Indicates the typical way an entity resides or occupies a place over time, such as its usual location, duration, or frequency of stay.
-
B.
housingPattern
Indicates the typical arrangement or distribution of housing units or residential structures within a given area or context.
-
C.
ownedResidence
Indicates that one entity has ownership of a dwelling or place of residence associated with another entity.
-
D.
residence
Indicates that one entity lives at, is based in, or habitually occupies the location represented by the other entity.
-
E.
residenceUsedFor
Indicates that a particular residence is used for a specific purpose, function, or activity.
- 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_69d85a121520819093dcce999fdefe1a |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e03c5f081908e4d14dbdbc7f7a6 |
completed | April 16, 2026, 1:40 a.m. |
| PD | Predicate disambiguation | batch_69deca9659f48190b8661df223ce5078 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:17 a.m.