Triple
T25188504
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charlie Cale |
E630793
|
entity |
| Predicate | abilityDescription |
P119478
|
FINISHED |
| Object | can always tell when someone is lying |
—
|
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: can always tell when someone is lying | Statement: [Charlie Cale, abilityDescription, can always tell when someone is lying]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: abilityDescription Context triple: [Charlie Cale, abilityDescription, can always tell when someone is lying]
-
A.
abilityDescribedAs
chosen
Indicates that an ability is characterized or expressed using a particular description or phrasing.
-
B.
ability
Indicates that an entity has the capacity or power to perform a particular action or achieve a specific outcome.
-
C.
abilityRange
Indicates the spatial or contextual extent within which an entity’s ability, power, or effect can be applied or is valid.
-
D.
accessDescribedAs
Indicates that the manner, conditions, or nature of access to something is characterized or specified by a particular description.
-
E.
capabilityType
Indicates the type or category of capability that an entity possesses or is associated with.
- 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_69e75a8a6d088190ba1e82a4345225e7 |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f46e0bbd2c8190a30a70dcf5523875 |
completed | May 1, 2026, 9:10 a.m. |
| PD | Predicate disambiguation | batch_69f44d8043b081908bbffd7f044b4f26 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 21, 2026, 12:44 p.m.