Triple
T28573891
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Henry Hill |
E723181
|
entity |
| Predicate | leftWitnessProtectionProgram |
P164648
|
FINISHED |
| Object | early 1990s |
—
|
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: early 1990s | Statement: [Henry Hill, leftWitnessProtectionProgram, early 1990s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leftWitnessProtectionProgram Context triple: [Henry Hill, leftWitnessProtectionProgram, early 1990s]
-
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.
evidenceOfProtection
Indicates that something serves as proof or indication that protection or safeguarding is present or has occurred.
-
C.
protectedBy
Indicates that one entity provides protection, defense, or safeguarding for another entity.
-
D.
canCallAsWitness
Indicates that one party is permitted or eligible to summon another party to provide testimony as a witness in a proceeding.
-
E.
laterProtects
Indicates that one entity provides protection for another entity at a later point in time than some referenced event or protection.
- F. None of above. chosen
Provenance (4 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_69f01d7e97708190ae9e77ee66a68abd |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f650949c5c8190a46dbdc76dfb5c33 |
completed | May 2, 2026, 7:29 p.m. |
| PD | Predicate disambiguation | batch_69f64cb0d8008190912e1430cfaf92aa |
completed | May 2, 2026, 7:12 p.m. |
| PDg | Predicate description generation | batch_69f64db8ee1881909362701d72ffe282 |
completed | May 2, 2026, 7:17 p.m. |
Created at: April 28, 2026, 4:11 a.m.