Triple
T22690377
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IL-17A |
E561033
|
entity |
| Predicate | formsHeterodimer |
P142516
|
FINISHED |
| Object | IL-17A/F heterodimer |
—
|
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: IL-17A/F heterodimer | Statement: [IL-17A, formsHeterodimer, IL-17A/F heterodimer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formsHeterodimer Context triple: [IL-17A, formsHeterodimer, IL-17A/F heterodimer]
-
A.
formsWeakDoubletWith
Indicates that one entity forms a weakly interacting or loosely coupled pair (doublet) with another entity, typically in contrast to a stronger or more tightly bound association.
-
B.
formedDuoWith
Indicates that two entities joined together to create a duo, typically collaborating or acting as a pair for a shared purpose or activity.
-
C.
dualPair
Indicates that two entities form a dual pair, standing in a mathematically defined dual relationship where each is the dual counterpart of the other.
-
D.
formsInteractingPairWith
chosen
Indicates that one entity forms a mutually interacting pair or duo with another entity, such that their behaviors or effects are directly linked.
-
E.
formsHorseshoeWith
Indicates that one entity curves or arranges itself around another in a U-shaped, horseshoe-like configuration, partially enclosing or surrounding it.
- 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_69e2454d71b48190a1f80af9f82b6fcf |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1789a1fd08190bce5fa0babe695d3 |
completed | April 29, 2026, 3:18 a.m. |
| PD | Predicate disambiguation | batch_69ee62b2259c819091ed1387a748b9f3 |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 17, 2026, 3:13 p.m.