Triple
T4768353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michal |
E105865
|
entity |
| Predicate | emotionDuringDavidDance |
P57237
|
FINISHED |
| Object | despised him in her heart |
—
|
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: despised him in her heart | Statement: [Michal, emotionDuringDavidDance, despised him in her heart]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: emotionDuringDavidDance Context triple: [Michal, emotionDuringDavidDance, despised him in her heart]
-
A.
emotionalDynamic
chosen
Indicates how emotions, moods, or affective states change, interact, or influence each other between entities over time.
-
B.
hasDanceChoreography
Indicates that an entity is associated with or characterized by a specific dance choreography.
-
C.
continuedToDanceDespite
Indicates that one entity kept dancing even though a particular condition, event, or obstacle occurred that might normally have caused them to stop.
-
D.
emotionEffect
Indicates that one entity’s emotional state causes or influences a change in another entity’s feelings, behavior, or condition.
-
E.
danceCreated
Indicates that one entity is the creator or choreographer of a particular dance or dance work.
- 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_69bd43f226fc8190b867cc249c2a9042 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6537eb80819096e0ae906c59d605 |
completed | March 20, 2026, 3:18 p.m. |
| PD | Predicate disambiguation | batch_69bd6229d8448190a271719e5e30fd82 |
completed | March 20, 2026, 3:05 p.m. |
Created at: March 20, 2026, 1:21 p.m.