Triple
T25597518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Judy Shepard |
E641693
|
entity |
| Predicate | hasSpeakingFocus |
P9850
|
FINISHED |
| Object | hate crimes |
—
|
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: hate crimes | Statement: [Judy Shepard, hasSpeakingFocus, hate crimes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpeakingFocus Context triple: [Judy Shepard, hasSpeakingFocus, hate crimes]
-
A.
hasProgramFocus
Indicates that an entity (such as a program or initiative) is oriented around or primarily concerned with a particular thematic area, topic, or objective.
-
B.
hasSpeakerStatus
Indicates that an entity holds a particular role, rank, or status in the context of speaking or serving as a speaker.
-
C.
hasActingFocus
Indicates that an entity is the primary performer or focal agent carrying out an action in a given context.
-
D.
hasSpeech
chosen
Indicates that an entity produces, delivers, or is associated with a spoken utterance or verbal expression.
-
E.
hasGameFocus
Indicates that something is primarily concerned with, oriented toward, or centered around games or gaming activities.
- 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_69e75dc60d108190b7e2419e36b0134b |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f67257b0448190a13011af81c81449 |
completed | May 2, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69f66ec3d3d48190ab2f2b71939e572e |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 21, 2026, 4:28 p.m.