Triple
T22977597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alma Coin |
E571367
|
entity |
| Predicate | relationshipTypeWithKatnissEverdeen |
P150474
|
FINISHED |
| Object | initially ally then adversary |
—
|
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: initially ally then adversary | Statement: [Alma Coin, relationshipTypeWithKatnissEverdeen, initially ally then adversary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWithKatnissEverdeen Context triple: [Alma Coin, relationshipTypeWithKatnissEverdeen, initially ally then adversary]
-
A.
relationshipToCharacter
Indicates the specific type of personal, social, or narrative connection that one entity has to a given character.
-
B.
relationshipType
Indicates the specific kind of relationship that exists between two or more entities.
-
C.
relationshipToPeeta
Indicates the specific interpersonal or familial connection that one entity has to Peeta.
-
D.
characterActorRelationship
Indicates a relationship where an actor portrays or is associated with a specific character in a work.
-
E.
relationshipTypeWithTristan
Indicates the specific nature or category of the relationship that an entity has with Tristan.
- 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_69e245b3c50481908bb3741ec9f40862 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18292f3788190ab4e9d559e0070c8 |
completed | April 29, 2026, 4:01 a.m. |
| PD | Predicate disambiguation | batch_69ef3b9101f48190a06c69dff26c6441 |
completed | April 27, 2026, 10:33 a.m. |
| PDg | Predicate description generation | batch_69ef538a115081908982597f79355840 |
completed | April 27, 2026, 12:16 p.m. |
Created at: April 17, 2026, 3:48 p.m.