Triple
T3250273
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joe Starks |
E68159
|
entity |
| Predicate | conflictWithJanieCrawford |
P4897
|
FINISHED |
| Object | publicly insults and belittles her |
—
|
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: publicly insults and belittles her | Statement: [Joe Starks, conflictWithJanieCrawford, publicly insults and belittles her]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conflictWithJanieCrawford Context triple: [Joe Starks, conflictWithJanieCrawford, publicly insults and belittles her]
-
A.
conflictWith
chosen
Indicates that two entities are in opposition or disagreement, such that their goals, actions, or states are incompatible or interfere with each other.
-
B.
reportedConflict
Indicates that one party has formally reported the existence of a conflict involving another party or situation.
-
C.
addressedConflictWith
Indicates that one entity has taken action to confront, manage, or resolve a conflict involving another entity.
-
D.
notableConflictWith
Indicates a significant, recognized conflict or dispute that exists or has existed between the related entities.
-
E.
conflictRole
Indicates that an entity plays a specific role or position within a conflict or dispute between parties.
- 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_69ad858e4c708190aa31d486cfee8a6a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaf40f7908190a450c3136fccb020 |
completed | March 8, 2026, 5:17 p.m. |
| PD | Predicate disambiguation | batch_69ada41837e48190933572165be0ca38 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:09 p.m.