Triple
T25201042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lucas (The Hunt) |
E631125
|
entity |
| Predicate | stillFaces |
P158024
|
FINISHED |
| Object | lingering suspicion after exoneration |
—
|
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: lingering suspicion after exoneration | Statement: [Lucas (The Hunt), stillFaces, lingering suspicion after exoneration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stillFaces Context triple: [Lucas (The Hunt), stillFaces, lingering suspicion after exoneration]
-
A.
faceExpression
Indicates the specific facial expression an entity is displaying, capturing its visible emotional or expressive state.
-
B.
mayFace
Indicates that an entity is likely or permitted to encounter, experience, or be subjected to another entity or situation.
-
C.
stillType
Indicates that one entity is a specific type or category of "still" (e.g., a particular kind of stillness, still image, or distillation apparatus).
-
D.
turnedFace
Indicates that one entity directed or rotated its face toward another entity or specific direction.
-
E.
facesDeath
Indicates that an entity is confronting, experiencing, or is directly threatened by death or a life-ending situation.
- F. None of above. chosen
Provenance (4 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_69e75a8b86c4819089eda22c843b739f |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f474b5e4408190b726bbd038fa3862 |
completed | May 1, 2026, 9:39 a.m. |
| PD | Predicate disambiguation | batch_69f44d849e7c81909945438f40e35362 |
completed | May 1, 2026, 6:51 a.m. |
| PDg | Predicate description generation | batch_69f45300bd488190bb1d4160f5534ef6 |
completed | May 1, 2026, 7:15 a.m. |
Created at: April 21, 2026, 12:51 p.m.