Triple
T31954087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sokovian Accords |
E815857
|
entity |
| Predicate | primarySupporter |
P76672
|
FINISHED |
| Object | Tony Stark |
E70279
|
NE 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: Tony Stark | Statement: [Sokovian Accords, primarySupporter, Tony Stark]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primarySupporter Context triple: [Sokovian Accords, primarySupporter, Tony Stark]
-
A.
primaryPatron
Indicates that one entity serves as the main or chief supporter, sponsor, or benefactor of another entity.
-
B.
primaryParticipant
Indicates that an entity plays the main or most central role in a given event, activity, or relationship.
-
C.
primaryFor
Indicates that one entity serves as the main or principal option, resource, or association for another entity among possible alternatives.
-
D.
primaryEndorser
chosen
Indicates that an entity serves as the main or principal supporter, recommender, or approver of another entity or action.
-
E.
primaryCandidate
Indicates that an entity is the main or first-choice option among a set of candidates in a given context.
- F. None of above.
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_69f348f4ec708190abbb2a7c3ed58844 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a037c894b488190bcbec2eccaff4a01 |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2e8a4dbae0819085aaca09c5386f58 |
completed | June 14, 2026, 11:02 a.m. |
| PD | Predicate disambiguation | batch_6a0379eaa540819095a1c5d9f3513f9b |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 12:08 a.m.