Triple
T1906035
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Widow Douglas |
E38006
|
entity |
| Predicate | triesTo |
P10902
|
FINISHED |
| Object | civilize Huckleberry Finn |
—
|
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: civilize Huckleberry Finn | Statement: [Widow Douglas, triesTo, civilize Huckleberry Finn]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: triesTo Context triple: [Widow Douglas, triesTo, civilize Huckleberry Finn]
-
A.
triedAt
Indicates that an attempt to perform an action or achieve an outcome occurred at a specific time or place.
-
B.
triedBy
chosen
Indicates that an entity has made an attempt to perform an action on, or in relation to, another entity.
-
C.
rescueAttemptNumber
Indicates the ordinal count of distinct attempts made to carry out a rescue in a given rescue situation or operation.
-
D.
wasTriedFor
Indicates that a person or entity underwent a formal legal proceeding in which they were judged in relation to a specific alleged offense or charge.
-
E.
wasTriedBy
Indicates that a legal case or charge involving an entity was examined and judged in a trial conducted by another entity (such as a court or judge).
- 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_69a8862a26088190aae5243695aeefc0 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb34d94fc8190a5bf1e582c77c725 |
completed | March 7, 2026, 5:10 a.m. |
| PD | Predicate disambiguation | batch_69abafe9f8b0819086d8f6288511c66d |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:35 p.m.