Triple
T24263065
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sam Weber |
E604759
|
entity |
| Predicate | settingOfReunion |
P108093
|
FINISHED |
| Object | South Carolina house of Harold and Sarah Cooper |
—
|
NE NERFINISHED |
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: South Carolina house of Harold and Sarah Cooper | Statement: [Sam Weber, settingOfReunion, South Carolina house of Harold and Sarah Cooper]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: settingOfReunion Context triple: [Sam Weber, settingOfReunion, South Carolina house of Harold and Sarah Cooper]
-
A.
reunionType
Indicates the specific kind or category of reunion event that relates the involved entities.
-
B.
reunionContext
chosen
Indicates the situational setting, circumstances, or background in which a reunion between entities takes place.
-
C.
reunionWith
Indicates that two or more entities come back together after a period of separation or absence.
-
D.
marksReunionOf
Indicates that an event, action, or state brings previously separated or distant entities back together, signifying their reunion.
-
E.
hasReunion
Indicates that a reunion event or gathering occurs between the related entities.
- 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_69e29544c29c8190b023606eafe5d36a |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f28c691eb08190b6fbda8f187d7427 |
completed | April 29, 2026, 10:55 p.m. |
| PD | Predicate disambiguation | batch_69f1c450aa508190bc9d372a5f6ee47a |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 18, 2026, 12:06 a.m.