Triple
T37151259
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mosasaurus lagoon (Jurassic World) |
E920367
|
entity |
| Predicate | showIncludes |
P81597
|
FINISHED |
| Object | Mosasaurus leaping out of water |
—
|
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: Mosasaurus leaping out of water | Statement: [Mosasaurus lagoon (Jurassic World), showIncludes, Mosasaurus leaping out of water]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: showIncludes Context triple: [Mosasaurus lagoon (Jurassic World), showIncludes, Mosasaurus leaping out of water]
-
A.
includesShow
chosen
Indicates that one entity contains or features a particular show as part of its content or offerings.
-
B.
outputIncludes
Indicates that the result or product of a process, function, or action contains or incorporates a specified element or component.
-
C.
includesSee
Indicates that one entity’s scope, content, or experience contains or encompasses the act of seeing or visual perception involving another entity.
-
D.
selectionIncludes
Indicates that a chosen set or subset explicitly contains or covers the specified element(s) as part of the selection.
-
E.
includedWith
Indicates that one entity is provided or packaged together as part of another entity.
- 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_69f76e9f87c08190b4c8f7fafbd8345a |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb344c60f8819090f2e21e1e61d621 |
completed | May 6, 2026, 12:30 p.m. |
| PD | Predicate disambiguation | batch_69fb2f642db08190b562725502c74ea6 |
completed | May 6, 2026, 12:09 p.m. |
Created at: May 3, 2026, 4:15 p.m.