Triple
T37827606
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Citadels |
E943107
|
entity |
| Predicate | primaryInteractionType |
P80144
|
FINISHED |
| Object | indirect conflict |
—
|
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: indirect conflict | Statement: [Citadels, primaryInteractionType, indirect conflict]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryInteractionType Context triple: [Citadels, primaryInteractionType, indirect conflict]
-
A.
primaryInteraction
chosen
Indicates the main or most significant interaction occurring between the involved entities.
-
B.
primaryEngagement
Indicates the main or most significant interaction, involvement, or relationship that an entity has with another entity or activity.
-
C.
primaryIntent
Indicates the main purpose, goal, or motivation underlying an action, event, or relationship among entities.
-
D.
primaryMode
Indicates the main or most commonly used method, manner, or form in which an action, process, or interaction is carried out between entities.
-
E.
usedInteractionType
Indicates the specific type or category of interaction that was used between the related entities.
- 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_69f76eea4c8c8190a335aed5955cf2db |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1772e48190ba738c6d11b321e2 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:19 p.m.