Triple
T37876873
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Formics |
E944747
|
entity |
| Predicate | keyHumanAdversary |
P188123
|
FINISHED |
| Object | Ender Wiggin |
—
|
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: Ender Wiggin | Statement: [Formics, keyHumanAdversary, Ender Wiggin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyHumanAdversary Context triple: [Formics, keyHumanAdversary, Ender Wiggin]
-
A.
hasKeyAdversary
chosen
Indicates that an entity has a primary or significant opposing force or rival that actively works against it.
-
B.
commonAdversary
Indicates that two or more entities share the same opponent, rival, or threat.
-
C.
modelsAdversary
Indicates that one entity represents, simulates, or formally characterizes another entity as an adversary within a given context or system.
-
D.
otherAdversary
Indicates that one entity is an adversary of another, distinct from any primary or previously identified adversary.
-
E.
keyFortress
Indicates that one entity functions as a key or means of access, control, or unlocking for a particular fortress or strongly secured place represented by the other 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_69f76eef55d481908ca6660b4b532550 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbbae559a8819086ef839973f8d9b2 |
completed | May 6, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69fbb1440fa08190abf25ba684f75b6e |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:19 p.m.