Triple
T36557517
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wars of Angmar against Arnor |
E901734
|
entity |
| Predicate | hasEnemyOfArnor |
P53524
|
FINISHED |
| Object | Witch-king of Angmar |
—
|
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: Witch-king of Angmar | Statement: [Wars of Angmar against Arnor, hasEnemyOfArnor, Witch-king of Angmar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEnemyOfArnor Context triple: [Wars of Angmar against Arnor, hasEnemyOfArnor, Witch-king of Angmar]
-
A.
wasEnemyOf
Indicates that one entity regarded or interacted with another as an adversary or opponent, typically in a hostile or conflicting relationship.
-
B.
opponentInBattleOfTheMorannon
Indicates that two entities were opposing sides facing each other in the Battle of the Morannon.
-
C.
Listoghil
Indicates a relationship in which an entity is associated with or belongs to the place or context referred to as Listoghil.
-
D.
hasFriendEnemyRelationshipWith
Indicates a relationship where two entities are simultaneously connected as both friends and enemies, reflecting a mixed or ambivalent association between them.
-
E.
hasOpposingFaction
chosen
Indicates that one faction stands in opposition or conflict to another faction.
- 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_69f76e634e9481908c9ba1b87ab87c26 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fdd07a34c08190982b8c61c2775cf6 |
completed | May 8, 2026, noon |
| PD | Predicate disambiguation | batch_69fdbd25c7908190b72fca8de7ce503f |
completed | May 8, 2026, 10:38 a.m. |
Created at: May 3, 2026, 4:11 p.m.