Triple
T37458819
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Goblin Blastmage |
E930865
|
entity |
| Predicate | flavorText |
P187898
|
FINISHED |
| Object | Goblin Blastmage is still figuring out where that last rocket went. |
—
|
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: Goblin Blastmage is still figuring out where that last rocket went. | Statement: [Goblin Blastmage, flavorText, Goblin Blastmage is still figuring out where that last rocket went.]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: flavorText Context triple: [Goblin Blastmage, flavorText, Goblin Blastmage is still figuring out where that last rocket went.]
-
A.
typicalFlavor
Indicates that something characteristically has or is associated with a particular flavor.
-
B.
isFlavored
Indicates that one entity imparts a particular taste or flavor characteristic to another entity.
-
C.
frostingFlavor
Indicates the specific flavor associated with a cake’s frosting in the relationship.
-
D.
meatFlavor
Indicates that one entity has the taste quality or flavor characteristic associated with meat in relation to another entity.
-
E.
primaryFlavor
Indicates the dominant or most characteristic taste associated with an item relative to other possible flavors.
- 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_69f76ec1a1148190b0a961f188d621b0 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb92efc5948190a040ba2028bab964 |
completed | May 6, 2026, 7:13 p.m. |
| PD | Predicate disambiguation | batch_69fb8d0b52588190bb29937a43b99b5e |
completed | May 6, 2026, 6:48 p.m. |
| PDg | Predicate description generation | batch_69fb92ee27408190b0116ef2d789abac |
completed | May 6, 2026, 7:13 p.m. |
Created at: May 3, 2026, 4:17 p.m.