Triple
T24165715
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John "Joker" Jackson |
E598977
|
entity |
| Predicate | chainedTo |
P81670
|
FINISHED |
| Object | Noah Cullen |
—
|
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: Noah Cullen | Statement: [John "Joker" Jackson, chainedTo, Noah Cullen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chainedTo Context triple: [John "Joker" Jackson, chainedTo, Noah Cullen]
-
A.
chainedAt
chosen
Indicates that one entity is physically secured to another (or to a fixed point) using a chain, restricting its movement or separation.
-
B.
hasChainDepicted
Indicates that an entity has a chain (or chains) visually represented as part of its depiction.
-
C.
attachedTo
Indicates that one entity is physically or logically fastened, connected, or joined to another entity.
-
D.
compositionallyLinkedTo
Indicates that one entity is connected to another as part of a larger composition, such that changes or properties of one are meaningfully related to the combined whole.
-
E.
chains
Indicates that one entity is physically or metaphorically bound, linked, or restrained by another through chains or a chain-like connection.
- 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_69e288cbd62881909de32ca64a70c17b |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f27c9ddfcc819096697a844b300cce |
completed | April 29, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69f1c42f942c8190b103ff29a60fef34 |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 17, 2026, 11:32 p.m.