Triple
T28974534
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rangers of Ithilien |
E734371
|
entity |
| Predicate | enemyForcesObserved |
P39676
|
FINISHED |
| Object | Haradrim |
—
|
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: Haradrim | Statement: [Rangers of Ithilien, enemyForcesObserved, Haradrim]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: enemyForcesObserved Context triple: [Rangers of Ithilien, enemyForcesObserved, Haradrim]
-
A.
primaryEnemyForces
Indicates that the related entities constitute the main opposing or hostile forces in a conflict or competitive situation.
-
B.
enemyForceType
Indicates that one entity is characterized as a hostile or opposing force of a specified type relative to another entity.
-
C.
commandedForcesAgainst
Indicates that one entity held command authority over military or armed forces engaged in opposition to another entity.
-
D.
besiegingForce
Indicates a military group that is surrounding and attacking a target location or force in an attempt to capture or subdue it.
-
E.
engagedForces
chosen
Indicates that one force has actively committed or deployed its military units against another force in combat or operational interaction.
- 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_69f05b0d1e7c819092baab93d3fe277e |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f65f7731e4819099d5bd3d915ee266 |
completed | May 2, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f65c2198208190a3954086c22cfcbf |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 9:07 a.m.