Triple
T32196272
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | programmed cell death protein 1 |
E822411
|
entity |
| Predicate | roleInTolerance |
P165140
|
FINISHED |
| Object | prevents autoimmunity |
—
|
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: prevents autoimmunity | Statement: [programmed cell death protein 1, roleInTolerance, prevents autoimmunity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInTolerance Context triple: [programmed cell death protein 1, roleInTolerance, prevents autoimmunity]
-
A.
approximateRole
Indicates a relationship where one entity serves in a role that is similar to, but not exactly the same as, the specified role for another entity.
-
B.
roleAccordingTo
Indicates that an entity holds a particular role or function as defined or interpreted by a specified source or perspective.
-
C.
rangeRole
Indicates that the specified role is associated with, or applies to, the range (target) of a property or relationship.
-
D.
roleOn
chosen
Indicates that an entity holds or performs a specific role or function within another entity, context, or activity.
-
E.
roleInvolves
Indicates that a particular role includes or requires participation in a specified activity, responsibility, or function.
- 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_69f349093174819086e633c190a51aa8 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a000efe971081909de03f875a7ad6cc |
completed | May 10, 2026, 4:52 a.m. |
| PD | Predicate disambiguation | batch_6a000c4ffe788190a5757af60aadd9f3 |
completed | May 10, 2026, 4:40 a.m. |
Created at: May 1, 2026, 12:36 a.m.