Triple
T31954142
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lagos incident |
E815858
|
entity |
| Predicate | keyHeroInvolved |
P100004
|
FINISHED |
| Object | Steve Rogers |
—
|
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: Steve Rogers | Statement: [Lagos incident, keyHeroInvolved, Steve Rogers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyHeroInvolved Context triple: [Lagos incident, keyHeroInvolved, Steve Rogers]
-
A.
championInvolved
Indicates that a champion (or leading figure) is actively participating in or associated with the specified event, activity, or context.
-
B.
playerInvolved
Indicates that a specific player participates in, is associated with, or takes part in a particular event, action, or situation.
-
C.
includesHeroes
Indicates that something (such as a work, group, or collection) contains or features one or more heroes as part of it.
-
D.
linkedHero
Indicates a relationship where one hero is associated or connected to another hero in a meaningful way.
-
E.
baseHero
chosen
Indicates that one entity serves as the primary or foundational hero associated with another entity.
- 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_69f348f4ec708190abbb2a7c3ed58844 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b2ad90b88190934e67fff4bffe58 |
completed | May 3, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f6b151ad008190836c1bcdec503ce2 |
completed | May 3, 2026, 2:22 a.m. |
Created at: May 1, 2026, 12:08 a.m.