Triple
T21401561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vital Proteins |
E527923
|
entity |
| Predicate | hasHealthPositioning |
P134642
|
FINISHED |
| Object | supports skin elasticity |
—
|
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: supports skin elasticity | Statement: [Vital Proteins, hasHealthPositioning, supports skin elasticity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHealthPositioning Context triple: [Vital Proteins, hasHealthPositioning, supports skin elasticity]
-
A.
hasPositioning
Indicates that one entity occupies, is arranged in, or is assigned a specific spatial or relative position with respect to another entity or reference frame.
-
B.
safetyPositioning
Indicates the spatial or situational arrangement of entities to ensure or enhance safety.
-
C.
hasHealthArea
chosen
Indicates that an entity is associated with, or falls within the scope of, a particular health-related domain or area of concern.
-
D.
positionOnHealthCare
Indicates a person or entity’s stance, opinion, or policy preference regarding health care systems, services, or reforms.
-
E.
hasDynamicPositioning
Indicates that an entity is capable of automatically adjusting and maintaining its position relative to external references or conditions in real time.
- 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_69e0b520ee3c8190abddbee7e37e834c |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e8b1702b44819080b282c22d151c88 |
completed | April 22, 2026, 11:30 a.m. |
| PD | Predicate disambiguation | batch_69e61633f8208190a2a849457c4e4198 |
completed | April 20, 2026, 12:04 p.m. |
Created at: April 16, 2026, 5:18 p.m.