Triple
T33885674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Long political family |
E868625
|
entity |
| Predicate | hasProducedOffice |
P91143
|
FINISHED |
| Object | Governor of Louisiana |
—
|
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: Governor of Louisiana | Statement: [Long political family, hasProducedOffice, Governor of Louisiana]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasProducedOffice Context triple: [Long political family, hasProducedOffice, Governor of Louisiana]
-
A.
familyHasProducedOffice
chosen
Indicates that a particular family has produced at least one member who has held a specified office or position.
-
B.
hasProperOffice
Indicates that an entity maintains an officially designated, appropriate office or place of business.
-
C.
hasOffice
Indicates that an entity possesses or maintains an office at a particular location or within a specific organization.
-
D.
hasOfficeDevelopment
Indicates that an entity is associated with the planning, construction, or presence of office-related real estate development.
-
E.
hasOfficeBuildings
Indicates that one entity possesses, controls, or is associated with one or more office buildings.
- 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_69f34996761c8190864e42f7c9cf215b |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a02008fcf1c8190b5b6c285944c52e9 |
completed | May 11, 2026, 4:15 p.m. |
| PD | Predicate disambiguation | batch_6a01ffd3ba008190b6f026bd4e6b9a37 |
completed | May 11, 2026, 4:12 p.m. |
Created at: May 1, 2026, 1:48 a.m.