Triple
T260346
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth Howe |
E5526
|
entity |
| Predicate | posthumousRecognition |
P5766
|
FINISHED |
| Object | acknowledged as innocent by later historians |
—
|
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: acknowledged as innocent by later historians | Statement: [Elizabeth Howe, posthumousRecognition, acknowledged as innocent by later historians]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: posthumousRecognition Context triple: [Elizabeth Howe, posthumousRecognition, acknowledged as innocent by later historians]
-
A.
posthumousReputation
chosen
Indicates the reputation or standing attributed to a person after their death.
-
B.
canBeAwardedPosthumously
Indicates that something (such as an honor, title, or award) is eligible to be granted to a person after their death.
-
C.
isPosthumous
Indicates that something occurs, is created, or is conferred after the death of the person to whom it relates.
-
D.
commemoratedBy
Indicates that something is honored, remembered, or celebrated through a particular action, event, object, or representation.
-
E.
commemoratedIn
Indicates that something is honored, remembered, or recognized within a particular work, event, place, or medium.
- 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_69a2580a64ac8190ad76e34bb0715b5e |
completed | Feb. 28, 2026, 2:50 a.m. |
| NER | Named-entity recognition | batch_69a25f921c2881908821ca2c03815eae |
completed | Feb. 28, 2026, 3:22 a.m. |
| PD | Predicate disambiguation | batch_69a25b6b3ea88190bbd858999e42efae |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 2:55 a.m.