Triple
T3763403
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ansar Dine |
E82614
|
entity |
| Predicate | activeInEvent |
P50824
|
FINISHED |
| Object | 2012 insurgency in northern Mali |
—
|
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: 2012 insurgency in northern Mali | Statement: [Ansar Dine, activeInEvent, 2012 insurgency in northern Mali]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: activeInEvent Context triple: [Ansar Dine, activeInEvent, 2012 insurgency in northern Mali]
-
A.
hasActivityIn
Indicates that an entity engages in or performs a particular activity within a specified context, location, or domain.
-
B.
isActive
Indicates that an entity is currently functioning, engaged, or enabled within a given context or system.
-
C.
activeInFieldFrom
Indicates that an entity is professionally or actively engaged in a particular field starting from a specified point in time.
-
D.
activeFrom
Indicates the starting point in time from which an entity or relationship is considered active or in effect.
-
E.
activeInYear
Indicates that an entity was active, functioning, or operational during a specified year.
- F. None of above. chosen
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_69ad8b207b0081909d2b48843fbd8795 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcbfbecf8819099d80af480cbe2d2 |
completed | March 8, 2026, 7:20 p.m. |
| PD | Predicate disambiguation | batch_69adc04c851c8190ae5eaebf36df539b |
completed | March 8, 2026, 6:30 p.m. |
| PDg | Predicate description generation | batch_69adc0fe3e3c8190bd886c7745c172a0 |
completed | March 8, 2026, 6:33 p.m. |
Created at: March 8, 2026, 3:35 p.m.