Triple
T37592383
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cortex Island |
E935290
|
entity |
| Predicate | hasConnectionToCharacter |
P133079
|
FINISHED |
| Object | Crash Bandicoot |
E52157
|
NE 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: Crash Bandicoot | Statement: [Cortex Island, hasConnectionToCharacter, Crash Bandicoot]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasConnectionToCharacter Context triple: [Cortex Island, hasConnectionToCharacter, Crash Bandicoot]
-
A.
connectsCharacter
chosen
Indicates that one character is linked or associated with another in some meaningful way.
-
B.
belongsToCharacter
Indicates that something is owned, associated with, or under the domain of a particular character.
-
C.
hasCharacterAssociated
Indicates that one entity is linked to or connected with a particular character (such as a person, figure, or persona) in some relevant way.
-
D.
appliesToCharacter
Indicates that an action, rule, or property is specifically directed toward or relevant for a particular character.
-
E.
hasPlayableCharacter
Indicates that an entity includes or is associated with a character that a user can control or play as.
- F. None of above.
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_69f76ecf39c081909baffe597bb55273 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a40e0631b0c8190bec5bbc76d8e5235 |
completed | June 28, 2026, 8:50 a.m. |
| PD | Predicate disambiguation | batch_6a037a1553e08190bb7424c448cb1f33 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:18 p.m.