Triple
T23650519
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kymriah |
E584153
|
entity |
| Predicate | firstIndicationRegion |
P97650
|
FINISHED |
| Object | United States |
—
|
NE NERFINISHED |
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: United States | Statement: [Kymriah, firstIndicationRegion, United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstIndicationRegion Context triple: [Kymriah, firstIndicationRegion, United States]
-
A.
firstIndication
Indicates that something is the earliest or initial sign, symptom, or evidence pointing to a particular condition, event, or state.
-
B.
indicationRegion
Indicates that something serves as a sign, marker, or signal specifically associated with a particular geographic or spatial region.
-
C.
firstForRegion
chosen
Indicates that something is the earliest or primary instance of its kind within a specified region.
-
D.
firstReleaseRegion
Indicates the geographic region or market where something (such as a product, work, or release) was first made publicly available.
-
E.
primaryRecognitionRegion
Indicates the region that serves as the main or most authoritative area where a recognition, identification, or acknowledgment of something is established or applied.
- 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_69e248fefafc81909656921192f30e80 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b357d1108190802bc29e0ed7f097 |
completed | April 29, 2026, 7:29 a.m. |
| PD | Predicate disambiguation | batch_69f118d7903c8190bb590a71771e93af |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:49 p.m.