Triple
T32250604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Willie Stark |
E823869
|
entity |
| Predicate | relationshipTypeWithJackBurden |
P125661
|
FINISHED |
| Object | political patron |
—
|
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: political patron | Statement: [Willie Stark, relationshipTypeWithJackBurden, political patron]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWithJackBurden Context triple: [Willie Stark, relationshipTypeWithJackBurden, political patron]
-
A.
relationshipToJack
chosen
Indicates the specific type of personal or social connection an entity has with Jack.
-
B.
relationshipToJackBrown
Indicates the specific familial, social, or professional relationship that an entity has to Jack Brown.
-
C.
relationshipTypeWith Jim Burden
Indicates the specific nature or category of relationship that an entity has with Jim Burden.
-
D.
relationshipTypeWithJackieTaylor
Indicates the specific type or nature of the relationship that an entity has with Jackie Taylor.
-
E.
relationshipTypeWithJakeBarnes
Indicates the specific nature or category of relationship that an entity has with Jake Barnes.
- 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_69f3490cdda88190a9d61e11252a771f |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a037c894b488190bcbec2eccaff4a01 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379edf2d88190b492fca86ed23cac |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 12:40 a.m.