Triple
T19453900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hawkins National Laboratory |
E486685
|
entity |
| Predicate | coveredUp |
P25172
|
FINISHED |
| Object | Will Byers’ disappearance |
—
|
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: Will Byers’ disappearance | Statement: [Hawkins National Laboratory, coveredUp, Will Byers’ disappearance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coveredUp Context triple: [Hawkins National Laboratory, coveredUp, Will Byers’ disappearance]
-
A.
covered
Indicates that one entity lies over or on top of another entity so as to conceal, protect, or obscure it.
-
B.
coverUpBy
chosen
Indicates that one entity conceals, suppresses, or hides the actions, information, or wrongdoing associated with another entity.
-
C.
hiddenIn
Indicates that one entity is concealed within, behind, or inside another entity so that it is not readily visible or apparent.
-
D.
coverLocation
Indicates that one entity serves as a covering or protective layer positioned at or over a specific location of another entity.
-
E.
collapsedOn
Indicates that one entity physically fell or caved in onto another entity, ending up resting on or covering it.
- 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_69d8e8d86d608190bd199a98d0297f27 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e633c117ac8190a38c01c3191beaea |
completed | April 20, 2026, 2:10 p.m. |
| PD | Predicate disambiguation | batch_69e4fd7499a4819082bec0be8afba35c |
completed | April 19, 2026, 4:06 p.m. |
Created at: April 10, 2026, 1:38 p.m.