Triple
T29321012
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rebel Army |
E743513
|
entity |
| Predicate | notableEnemyCharacter |
P11706
|
FINISHED |
| Object | Marco Rossi |
E606685
|
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: Marco Rossi | Statement: [Rebel Army, notableEnemyCharacter, Marco Rossi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableEnemyCharacter Context triple: [Rebel Army, notableEnemyCharacter, Marco Rossi]
-
A.
enemyCharacter
Indicates that one character is hostile or opposed to another, typically treating them as an adversary or foe.
-
B.
notableBoss
Indicates that one entity is a boss or superior of another in a way that is particularly prominent, distinguished, or noteworthy.
-
C.
notableCombatant
Indicates that an entity is recognized as a significant or distinguished participant in a particular conflict or combat event.
-
D.
notableAdversary
chosen
Indicates that one entity is recognized as a significant or prominent opponent or rival of another entity.
-
E.
enemyCharacterIn
Indicates that a character is located within or present inside an enemy-controlled area, zone, or context.
- 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_69f09125f784819080f4e9fce9fe624f |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_6a0340784c488190aa6c7c9be2e8a434 |
completed | May 12, 2026, 3 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a25c0e88904819091cd0e5476547c82 |
completed | June 7, 2026, 7:05 p.m. |
| PD | Predicate disambiguation | batch_6a033f33eddc819091507716f6ed7d7d |
completed | May 12, 2026, 2:54 p.m. |
Created at: April 28, 2026, 1:23 p.m.