Triple
T28889111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caledon Hockley |
E732645
|
entity |
| Predicate | attemptsToControl |
P69335
|
FINISHED |
| Object | Rose DeWitt Bukater |
—
|
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: Rose DeWitt Bukater | Statement: [Caledon Hockley, attemptsToControl, Rose DeWitt Bukater]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: attemptsToControl Context triple: [Caledon Hockley, attemptsToControl, Rose DeWitt Bukater]
-
A.
aimsToControl
chosen
Indicates an intention or effort by one entity to gain power over, direct, or regulate another entity or situation.
-
B.
canControl
Indicates that one entity has the ability or authority to direct, manage, or influence the behavior or state of another entity.
-
C.
usedToControl
Indicates that one entity employed another as a means or tool to exercise control or regulation over something.
-
D.
endedControlOf
Indicates that one entity has ceased to exercise authority, influence, or governance over another entity or domain.
-
E.
affectedControlOf
Indicates that one entity has influenced, altered, or impacted the degree of control another entity has over something.
- 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_69f05b07bdec819080cadfe147aa1f25 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f65b14512c8190a40e70319dcc54cd |
completed | May 2, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69f659d02f1c8190831758ac52bb54e4 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 7:53 a.m.