Triple
T1574664
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Murder on Capitol Hill |
E33619
|
entity |
| Predicate | hasProtagonistRole |
P21567
|
FINISHED |
| Object | investigator of a congressional murder |
—
|
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: investigator of a congressional murder | Statement: [Murder on Capitol Hill, hasProtagonistRole, investigator of a congressional murder]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasProtagonistRole Context triple: [Murder on Capitol Hill, hasProtagonistRole, investigator of a congressional murder]
-
A.
hasProtagonist
Indicates that a work of narrative has a main character who serves as its central focus or driving agent.
-
B.
hasMainRole
Indicates that an entity holds the primary or most significant role in relation to another entity or context.
-
C.
mainProtagonist
Indicates that the subject is the central character or primary focus in the narrative of the related work.
-
D.
hasProtagonistRelationship
Indicates that there exists a central, story-driving relationship involving the protagonist and another entity within a narrative.
-
E.
featuresProtagonistOccupation
chosen
Indicates that the work’s main character has a specified occupation or job role.
- 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_69a885f27a4c8190a4622252cdf54c00 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a96083e7308190abbf025fe8e43abb |
completed | March 5, 2026, 10:52 a.m. |
| PD | Predicate disambiguation | batch_69a907ba63c88190b60c14dec8d1e40f |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:27 p.m.