Triple
T19157207
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Keytruda |
E468955
|
entity |
| Predicate | firstIndication |
P134649
|
FINISHED |
| Object | unresectable or metastatic melanoma |
—
|
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: unresectable or metastatic melanoma | Statement: [Keytruda, firstIndication, unresectable or metastatic melanoma]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstIndication Context triple: [Keytruda, firstIndication, unresectable or metastatic melanoma]
-
A.
first
Indicates that one entity precedes all others in an ordered sequence or ranking.
-
B.
firstOrdinary
Indicates that the subject is the first entity to hold or occupy an ordinary (non-special, standard) position, role, or status in a given sequence or context.
-
C.
previousIndication
Indicates that one indication or sign occurred earlier in time than another, serving as a prior instance or precursor in a sequence of indications.
-
D.
initialReception
Indicates the nature or quality of the first response or reaction something receives when it is introduced or presented.
-
E.
firstLabel
Indicates that the referenced label is the earliest or primary label assigned to an entity among a set of possible labels.
- F. None of above. chosen
Provenance (4 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_69d8dd084ff48190ac0f8c46ee722629 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5eeba91a081909c04d61d6117da06 |
completed | April 20, 2026, 9:15 a.m. |
| PD | Predicate disambiguation | batch_69e4b9b83d6881908e6271c620f74100 |
completed | April 19, 2026, 11:17 a.m. |
| PDg | Predicate description generation | batch_69e4bfe9ef7081908a74a57d1fc731ea |
completed | April 19, 2026, 11:43 a.m. |
Created at: April 10, 2026, 12:06 p.m.