Triple
T2815887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bloody Sunday (March 7, 1965) |
E54284
|
entity |
| Predicate | John LewisRole |
P37715
|
FINISHED |
| Object | SNCC leader and march co-leader |
—
|
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: SNCC leader and march co-leader | Statement: [Bloody Sunday (March 7, 1965), John LewisRole, SNCC leader and march co-leader]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: John LewisRole Context triple: [Bloody Sunday (March 7, 1965), John LewisRole, SNCC leader and march co-leader]
-
A.
Sam Rayburn role
Indicates the specific official position or capacity in which Sam Rayburn served or acted.
-
B.
notableOfficeHolder
Indicates that an entity is a significant or distinguished holder of a particular office or position associated with another entity.
-
C.
notableHistoricalFigureRole
chosen
Indicates that an entity is recognized as a historically significant person who played a particular role or held a specific position in history.
-
D.
houseMinorityLeader
Indicates the relationship in which a person holds the position of leader of the minority party in a legislative house.
-
E.
notableLeaderUS
Indicates that the subject is a prominent or historically significant leader associated with the United States.
- 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_69ab49de0af08190b3da69683be1e728 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abde4ed4ac81909f1ec4a3f7869bc1 |
completed | March 7, 2026, 8:14 a.m. |
| PD | Predicate disambiguation | batch_69abdd0740208190911dc9c9546a79ae |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 9:59 p.m.