Triple
T26650434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lowell Mather |
E669033
|
entity |
| Predicate | reasonForWitnessProtection |
P24667
|
FINISHED |
| Object | testifies against a crime family |
—
|
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: testifies against a crime family | Statement: [Lowell Mather, reasonForWitnessProtection, testifies against a crime family]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reasonForWitnessProtection Context triple: [Lowell Mather, reasonForWitnessProtection, testifies against a crime family]
-
A.
hasWitnessProtectionMeasures
Indicates that protective actions or safeguards are in place to shield a witness from potential threats or harm related to their testimony.
-
B.
protectsFromArrest
Indicates a relationship where one party provides legal or practical protection that prevents another party from being arrested.
-
C.
reasonForRaid
Indicates the underlying cause, motive, or justification for which a raid was initiated or carried out.
-
D.
protectionReason
chosen
Indicates the justification or cause for which protection is provided or required in the relationship between entities.
-
E.
leftWitnessProtectionProgram
Indicates that an entity has exited or is no longer participating in a witness protection program.
- 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_69ee9d00eb5481908d6c6d0ada2f0c9a |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f6cee45590819086e489bfccbe4ac3 |
completed | May 3, 2026, 4:28 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1188708190b8f0f56e595e6057 |
completed | May 3, 2026, 4:16 a.m. |
Created at: April 27, 2026, 2:32 a.m.