Triple
T17731763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edith Smith |
E442602
|
entity |
| Predicate | hasFullPowersOfArrest |
P55637
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Edith Smith, hasFullPowersOfArrest, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFullPowersOfArrest Context triple: [Edith Smith, hasFullPowersOfArrest, true]
-
A.
hasSubpoenaPower
Indicates that an entity possesses the legal authority to issue subpoenas compelling others to provide testimony or evidence.
-
B.
hasReasonForArrest
Indicates that an arrest is associated with a specific reason or cause.
-
C.
hasLegalAuthorityFrom
Indicates that one entity possesses formal legal power, rights, or authorization that originates from or is granted by another entity.
-
D.
lawEnforcementPowers
chosen
Indicates that an entity possesses official authority and legal powers to enforce laws, maintain public order, and carry out related policing actions.
-
E.
hasCriminalJurisdictionOver
Indicates that one authority or legal body holds the power to investigate, prosecute, and adjudicate criminal offenses committed within a specified scope or territory in relation to another entity.
- 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_69d8b9ec79688190b86bdcef85a7b3aa |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e478e7773081909dadb90ff5cb0906 |
completed | April 19, 2026, 6:40 a.m. |
| PD | Predicate disambiguation | batch_69e3cde815e08190881972e2d80d151e |
completed | April 18, 2026, 6:31 p.m. |
Created at: April 10, 2026, 10:08 a.m.