Triple
T29655155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dark Archon |
E750243
|
entity |
| Predicate | requiresUnitToMerge |
P184765
|
FINISHED |
| Object | Dark Templar |
—
|
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: Dark Templar | Statement: [Dark Archon, requiresUnitToMerge, Dark Templar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: requiresUnitToMerge Context triple: [Dark Archon, requiresUnitToMerge, Dark Templar]
-
A.
canMerge
Indicates that two or more entities are compatible in such a way that they can be combined into a single unified entity or structure.
-
B.
unificationRequirement
chosen
Indicates that certain entities must be combined or made consistent according to specified rules or conditions before a relationship or operation can proceed.
-
C.
intendedToMerge
Indicates that one entity had the purpose or plan to combine or consolidate with another entity into a single unit.
-
D.
hasMerger
Indicates a relationship where two or more entities combine into a single entity through a merger event.
-
E.
hasMerge
Indicates that one entity has been combined or integrated with another into a single, unified 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_69f0d6226fe881908819197c9ef9ee04 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69fdb04ed81c8190b8feea90c1c785a6 |
completed | May 8, 2026, 9:43 a.m. |
| PD | Predicate disambiguation | batch_69fda9d6c5148190a63205b6d9b0a1b4 |
completed | May 8, 2026, 9:16 a.m. |
Created at: April 28, 2026, 6:54 p.m.