Triple
T24070501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Howard |
E596211
|
entity |
| Predicate | cameraConcealmentMethod |
P94192
|
FINISHED |
| Object | strapped camera to his ankle |
—
|
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: strapped camera to his ankle | Statement: [Tom Howard, cameraConcealmentMethod, strapped camera to his ankle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cameraConcealmentMethod Context triple: [Tom Howard, cameraConcealmentMethod, strapped camera to his ankle]
-
A.
concealmentType
chosen
Indicates the specific manner or method by which something is hidden, obscured, or kept from detection.
-
B.
canCamouflage
Indicates that an entity has the ability to blend into its surroundings or alter its appearance to avoid detection.
-
C.
cameraStyle
Indicates the characteristic visual approach or technique used by a camera in capturing or presenting imagery.
-
D.
usesMasksOrDisguises
Indicates that an entity employs masks, costumes, or other forms of disguise to conceal or alter its identity in the context of an action or interaction.
-
E.
methodOfInfiltration
Indicates the specific technique or approach used to secretly gain access to or penetrate a target, system, or organization.
- 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_69e288c25c008190850cf447940ab181 |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1db17c99881909f97e858fb183d86 |
completed | April 29, 2026, 10:19 a.m. |
| PD | Predicate disambiguation | batch_69f1764b1d4c8190b12590c6339c31c1 |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 10:41 p.m.