Triple
T25139790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ambush |
E629768
|
entity |
| Predicate | actorForCaptBenLorrison |
P157965
|
FINISHED |
| Object | John Hodiak |
—
|
NE NERFINISHED |
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: John Hodiak | Statement: [Ambush, actorForCaptBenLorrison, John Hodiak]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: actorForCaptBenLorrison Context triple: [Ambush, actorForCaptBenLorrison, John Hodiak]
-
A.
James Pearson
Indicates a relationship or action involving the entity named "James Pearson" and another entity, event, or attribute, depending on context.
-
B.
Lincoln Lewis
Indicates a relationship or association involving the entity or name "Lincoln Lewis," such as authorship, participation, or attribution in a given context.
-
C.
Jack Hively
Indicates a relationship or action involving the person named Jack Hively, such as authorship, direction, or participation in a work or event.
-
D.
Joseph Alioto
Indicates a relationship or action involving the person named Joseph Alioto, such as authorship, participation, or association in a given context.
-
E.
laterCaptain
Indicates that one entity becomes the captain of something at a later time than another referenced captain or captaincy.
- 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_69e2ff338250819096ff6c8892804389 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f468475218819089b73a0d2e072110 |
completed | May 1, 2026, 8:45 a.m. |
| PD | Predicate disambiguation | batch_69f44d8043b081908bbffd7f044b4f26 |
completed | May 1, 2026, 6:51 a.m. |
| PDg | Predicate description generation | batch_69f45300bd488190bb1d4160f5534ef6 |
completed | May 1, 2026, 7:15 a.m. |
Created at: April 18, 2026, 6:29 a.m.