Triple
T3308663
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Henry Furman |
E69514
|
entity |
| Predicate | sentenceModifiedTo |
P25699
|
FINISHED |
| Object | life imprisonment |
—
|
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: life imprisonment | Statement: [William Henry Furman, sentenceModifiedTo, life imprisonment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sentenceModifiedTo Context triple: [William Henry Furman, sentenceModifiedTo, life imprisonment]
-
A.
sentenceModification
chosen
Indicates that one sentence alters, qualifies, or elaborates on the meaning, structure, or content of another sentence.
-
B.
laterModification
Indicates that one entity is a modification or revision that occurs after another in time.
-
C.
amendedFor
Indicates that one entity has been modified or revised specifically to address, correct, or accommodate another entity.
-
D.
sentenceReducedTo
Indicates that one sentence is a simplified, shortened, or compressed form derived from another sentence.
-
E.
modification
Indicates a change made to an existing entity, altering its properties, structure, or state from a prior version.
- 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_69ad859f218081909458d2cebbf57565 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb0e9f33c81909cff835a83e0a657 |
completed | March 8, 2026, 5:24 p.m. |
| PD | Predicate disambiguation | batch_69ada4282730819092aa39c5f9269df0 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:11 p.m.