Triple
T32626996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walter Collins |
E834084
|
entity |
| Predicate | caseLedTo |
P18658
|
FINISHED |
| Object | public criticism of LAPD in late 1920s |
—
|
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: public criticism of LAPD in late 1920s | Statement: [Walter Collins, caseLedTo, public criticism of LAPD in late 1920s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: caseLedTo Context triple: [Walter Collins, caseLedTo, public criticism of LAPD in late 1920s]
-
A.
canLeadTo
chosen
Indicates that one entity, condition, or event has the potential to cause, result in, or bring about another.
-
B.
caseReached
Indicates that a particular case, situation, or legal matter has arrived at, been brought before, or come under the consideration of a specified authority, stage, or entity.
-
C.
caseLoad
Indicates the number or collection of cases, tasks, or matters currently assigned to or handled by an entity.
-
D.
leadingCaseOn
Indicates that one case serves as the primary or authoritative precedent for another case.
-
E.
caseLocation
Indicates the specific place or jurisdiction in which a case or legal matter is situated, filed, or adjudicated.
- 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_69f3492ccc80819086ef7d26e9786647 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6c8159edc8190b1c87015e0c820e8 |
completed | May 3, 2026, 3:59 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f42fbc8190a06eb1044c9e6094 |
completed | May 3, 2026, 3:41 a.m. |
Created at: May 1, 2026, 1:06 a.m.