Triple
T29655116
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Archon |
E750242
|
entity |
| Predicate | weakAgainst |
P47330
|
FINISHED |
| Object | long-range siege units |
—
|
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: long-range siege units | Statement: [Archon, weakAgainst, long-range siege units]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: weakAgainst Context triple: [Archon, weakAgainst, long-range siege units]
-
A.
effectivenessAgainst
Indicates how well one entity performs in countering, influencing, or mitigating the impact of another entity.
-
B.
hasWeakness
chosen
Indicates that one entity is vulnerable to, or can be adversely affected or defeated by, another entity.
-
C.
methodOfDefeat
Indicates the specific way or technique by which one entity defeats or overcomes another.
-
D.
initialWeakness
Indicates that an entity has a vulnerability or disadvantage present at the beginning of a process, event, or interaction.
-
E.
playstyleWeakness
Indicates a relationship where one playstyle is particularly vulnerable or disadvantaged when facing another playstyle.
- 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_69f66f274ba08190bcdbdfeccf4af09d |
completed | May 2, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69f6659f246081909821c5f452d14e8f |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 6:54 p.m.