Triple
T19772997
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prevnar 13 |
E474933
|
entity |
| Predicate | containsCarrierProtein |
P112356
|
FINISHED |
| Object | CRM197 |
—
|
NE NERFINISHED |
How this triple was built (4 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: CRM197 | Statement: [Prevnar 13, containsCarrierProtein, CRM197]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CRM197 Context triple: [Prevnar 13, containsCarrierProtein, CRM197]
-
A.
B197
B197 is a classified B-road in England that follows part of the historic Great North Road route.
-
B.
G.197
G.197 is an ITU-T standard that specifies objective methods for evaluating the performance and quality of digital audio coding systems.
-
C.
C219
C219 is the internal designation for the first-generation Mercedes-Benz CLS, a four-door luxury coupé produced in the mid-2000s that pioneered the modern "four-door coupé" segment.
-
D.
CRCM
CRCM is the stock ticker symbol for Care.com, an online marketplace that connects families with caregivers for childcare, senior care, and other household services.
-
E.
CM-017
CM-017 is the Apollo 4 command module, an uncrewed early Apollo spacecraft used by NASA to test the Saturn V rocket and reentry systems in 1967.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: CRM197 Target entity description: CRM197 is a non-toxic mutant form of diphtheria toxin widely used as a carrier protein in conjugate vaccines to enhance immune responses.
-
A.
B197
B197 is a classified B-road in England that follows part of the historic Great North Road route.
-
B.
G.197
G.197 is an ITU-T standard that specifies objective methods for evaluating the performance and quality of digital audio coding systems.
-
C.
C219
C219 is the internal designation for the first-generation Mercedes-Benz CLS, a four-door luxury coupé produced in the mid-2000s that pioneered the modern "four-door coupé" segment.
-
D.
CRCM
CRCM is the stock ticker symbol for Care.com, an online marketplace that connects families with caregivers for childcare, senior care, and other household services.
-
E.
CM-017
CM-017 is the Apollo 4 command module, an uncrewed early Apollo spacecraft used by NASA to test the Saturn V rocket and reentry systems in 1967.
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsCarrierProtein Context triple: [Prevnar 13, containsCarrierProtein, CRM197]
-
A.
hasProteinBinding
Indicates that one entity is capable of physically binding to or interacting specifically with a protein.
-
B.
isCarrierOf
Indicates that one entity serves as the bearer, holder, or transmitter of another entity (such as an object, substance, trait, or information).
-
C.
isMajorCarrierOf
Indicates that one entity serves as the primary or principal transporter or conveyor of another entity (such as goods, signals, or passengers).
-
D.
hasProtein
chosen
Indicates that one entity contains, includes, or is associated with a specific protein.
-
E.
hasProteinFeature
Indicates that a protein possesses a specific structural or functional feature, such as a domain, motif, or modification site.
- 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_69d8e51a43a08190956bc6df13c91a77 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6535e450c8190a2628245ae0d0bd3 |
completed | April 20, 2026, 4:25 p.m. |
| PD | Predicate disambiguation | batch_69e53053ed2881908400becdfada7fd3 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:48 p.m.