Triple
T37662088
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zombie Villager (Minecraft) |
E937738
|
entity |
| Predicate | sharesAIWith |
P28102
|
FINISHED |
| Object | Zombie (Minecraft) |
—
|
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: Zombie (Minecraft) | Statement: [Zombie Villager (Minecraft), sharesAIWith, Zombie (Minecraft)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesAIWith Context triple: [Zombie Villager (Minecraft), sharesAIWith, Zombie (Minecraft)]
-
A.
sharesBayWith
Indicates that two locations are situated along or adjacent to the same bay.
-
B.
sharesUniverseWith
chosen
Indicates that two entities exist within the same fictional or narrative universe, implying shared continuity, setting, or canon.
-
C.
sharesPlatformWith
Indicates that two entities operate on, are available through, or participate within the same platform or system.
-
D.
sharesRevenueWith
Indicates that one entity distributes a portion of its revenue to another entity as part of a revenue-sharing arrangement.
-
E.
sharesOpusWith
Indicates that two entities are associated with, contribute to, or are linked through the same work or opus.
- 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_69f76ed6df7c8190b018e5baea716ceb |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a00c07b302081908bf9755f8fdbc36e |
completed | May 10, 2026, 5:29 p.m. |
| PD | Predicate disambiguation | batch_6a00bfffb168819084b65804d601896d |
completed | May 10, 2026, 5:27 p.m. |
Created at: May 3, 2026, 4:18 p.m.