Triple
T36110804
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James Crichton |
E1044491
|
entity |
| Predicate | hasParticularNotableCharacteristic |
P201460
|
FINISHED |
| Object | prodigious memory |
—
|
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: prodigious memory | Statement: [James Crichton, hasParticularNotableCharacteristic, prodigious memory]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasParticularNotableCharacteristic Context triple: [James Crichton, hasParticularNotableCharacteristic, prodigious memory]
-
A.
notableFeatureOn
Indicates that one entity is a prominent or distinguishing feature located on or part of another entity.
-
B.
notableCollectionCharacteristic
Indicates that a collection is distinguished by a particular defining feature or quality that makes it notable.
-
C.
notableAppearanceFeature
Indicates that an entity is characterized by a distinctive or noteworthy physical appearance trait.
-
D.
hasHumanCharacteristic
Indicates that an entity possesses a trait, quality, or behavior typically associated with humans.
-
E.
notableTraitOnStage
Indicates that an entity is characterized by a distinctive or noteworthy trait specifically in the context of performing or appearing on stage.
- 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_69f76e344a4c8190af3858c6d78ba88f |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fff86e544c81908063f61b876c9d78 |
completed | May 10, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_69fff7e7cb688190977eeca41aad25b9 |
completed | May 10, 2026, 3:13 a.m. |
| PDg | Predicate description generation | batch_69fff86da6f48190aac10a80b648c05a |
completed | May 10, 2026, 3:15 a.m. |
Created at: May 3, 2026, 4:08 p.m.