Triple
T5381384
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portrait of Monsieur Bertin |
E113090
|
entity |
| Predicate | subjectAgeApproximation |
P45004
|
FINISHED |
| Object | middle-aged |
—
|
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: middle-aged | Statement: [Portrait of Monsieur Bertin, subjectAgeApproximation, middle-aged]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subjectAgeApproximation Context triple: [Portrait of Monsieur Bertin, subjectAgeApproximation, middle-aged]
-
A.
approximateAgeBeforePresent
Indicates that one entity’s age is an estimated value measured as a time interval before the present moment.
-
B.
containsAge
Indicates that one entity includes or specifies the age value or age-related information of another entity.
-
C.
ageModel
Indicates a relationship where one entity specifies or provides the age of another entity, typically in terms of a particular age value or age-related classification.
-
D.
numberOfAges
Indicates the count of distinct ages associated with an entity or within a specified group or context.
-
E.
ageStatus
chosen
Indicates the relationship between an entity and its classification into an age-related category or status (e.g., minor, adult, senior).
- 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_69bd4436a1988190af18dcff7fd306b4 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd88801b188190b9ac35ed89167fa3 |
completed | March 20, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69bd846172788190969f24bc7503c05e |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:03 p.m.