Triple
T17939133
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hemanta |
E448541
|
entity |
| Predicate | typicalHumanActivity |
P1164
|
FINISHED |
| Object | use of warm clothing at night |
—
|
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: use of warm clothing at night | Statement: [Hemanta, typicalHumanActivity, use of warm clothing at night]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalHumanActivity Context triple: [Hemanta, typicalHumanActivity, use of warm clothing at night]
-
A.
typicalActivity
chosen
Indicates that an entity is commonly or characteristically engaged in a particular activity.
-
B.
activityType
Indicates the specific kind or category of action or event that an entity is engaged in or associated with.
-
C.
mannerOfActivity
Indicates the way or style in which an activity is performed or carried out.
-
D.
activitiesCarriedOutFor
Indicates that certain activities are performed on behalf of, in service of, or for the benefit of a particular entity.
-
E.
activityStartApprox
Indicates that the start time of an activity is known only approximately, rather than as an exact timestamp.
- 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_69d8b9f79d14819095540856928f0e25 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4ad9455fc81908bf595f9ed42c624 |
completed | April 19, 2026, 10:25 a.m. |
| PD | Predicate disambiguation | batch_69e3f8e713d481908b4a126258c18b63 |
completed | April 18, 2026, 9:34 p.m. |
Created at: April 10, 2026, 10:21 a.m.