Triple
T28664667
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zihuatanejo (in film ending) |
E725555
|
entity |
| Predicate | firstExplicitlyMentionedBy |
P202020
|
FINISHED |
| Object | Andy Dufresne |
—
|
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: Andy Dufresne | Statement: [Zihuatanejo (in film ending), firstExplicitlyMentionedBy, Andy Dufresne]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstExplicitlyMentionedBy Context triple: [Zihuatanejo (in film ending), firstExplicitlyMentionedBy, Andy Dufresne]
-
A.
firstDocumentedBy
Indicates that one entity is the person or source that originally recorded, reported, or documented the other entity for the first time.
-
B.
firstAnnouncedBy
Indicates that one entity is the original source or originator that publicly disclosed, reported, or made known another entity or item for the first time.
-
C.
ageFirstMentioned
Indicates the point in time or age at which an entity is first referenced or mentioned in a given context.
-
D.
firstClearlyRecognizedIn
Indicates the point in time or context when something was first clearly identified, acknowledged, or distinguished as such.
-
E.
firstUsedBy
Indicates that something was initially utilized, applied, or employed by a particular entity before any others.
- 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_69f01d85be388190b669a0e401e2f2c4 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_6a00474f08908190bc8ae3b320ec887b |
completed | May 10, 2026, 8:52 a.m. |
| PD | Predicate disambiguation | batch_6a0045dc3bd48190a9e0520f3ef3f067 |
completed | May 10, 2026, 8:46 a.m. |
| PDg | Predicate description generation | batch_6a00474e552c8190b711363081d29292 |
completed | May 10, 2026, 8:52 a.m. |
Created at: April 28, 2026, 5 a.m.