Triple
T5090867
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Free Syrian Army |
E114747
|
entity |
| Predicate | fragmentation |
P58854
|
FINISHED |
| Object | experienced significant internal divisions |
—
|
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: experienced significant internal divisions | Statement: [Free Syrian Army, fragmentation, experienced significant internal divisions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fragmentation Context triple: [Free Syrian Army, fragmentation, experienced significant internal divisions]
-
A.
fragmentationLevel
chosen
Indicates the degree to which something is broken into smaller, separate parts or segments.
-
B.
successorStateFragmentation
Indicates that a successor state experiences division or breakup into multiple smaller political or administrative units.
-
C.
fracture
Indicates a relationship where an object or material is broken or cracked into parts, typically due to applied stress or impact.
-
D.
broken
Indicates that an entity is damaged or no longer functioning as intended, often as the result of some prior action or event.
-
E.
segmentation
Indicates dividing something into distinct parts or segments based on certain criteria or boundaries.
- 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_69bd443e941881908eb4e8c685b6f656 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7541b2bc8190b58c2a23733b7825 |
completed | March 20, 2026, 4:26 p.m. |
| PD | Predicate disambiguation | batch_69bd715c0a448190afc837c6c31dc6ab |
completed | March 20, 2026, 4:10 p.m. |
Created at: March 20, 2026, 1:40 p.m.