Triple
T34432073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fort Pienc |
E883854
|
entity |
| Predicate | partOfStatisticalUnit |
P87889
|
FINISHED |
| Object | District 2 – Eixample of Barcelona |
—
|
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: District 2 – Eixample of Barcelona | Statement: [Fort Pienc, partOfStatisticalUnit, District 2 – Eixample of Barcelona]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfStatisticalUnit Context triple: [Fort Pienc, partOfStatisticalUnit, District 2 – Eixample of Barcelona]
-
A.
partOfStatisticalSystem
Indicates that one entity functions as a component or subsystem within a broader statistical system or framework.
-
B.
statisticalUnitOf
Indicates that one entity serves as the statistical unit (the basic unit of observation or analysis) for which data or statistics are collected or reported about another entity.
-
C.
partOfPeople
Indicates that one group or individual is a subset or component of a larger group of people.
-
D.
structurePartOf
chosen
Indicates that one structure is a constituent or component of a larger, encompassing structure.
-
E.
partOfSingle
Indicates that one entity is a component or member of exactly one specific whole or collection, and not shared among multiple such wholes.
- 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_69f349c3dd2c819092cc9e64809f4a42 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a0048697bd081909073640666ca6a96 |
completed | May 10, 2026, 8:57 a.m. |
| PD | Predicate disambiguation | batch_6a0047bf3c248190a9ac97a7afdfe2cb |
completed | May 10, 2026, 8:54 a.m. |
Created at: May 1, 2026, 2 a.m.