Triple
T23504411
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ISIS forces in Iraq |
E572241
|
entity |
| Predicate | capturedTerritoryIn |
P77284
|
FINISHED |
| Object | Mosul |
—
|
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: Mosul | Statement: [ISIS forces in Iraq, capturedTerritoryIn, Mosul]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capturedTerritoryIn Context triple: [ISIS forces in Iraq, capturedTerritoryIn, Mosul]
-
A.
acquiredTerritoryFrom
Indicates that one entity gained control or ownership of a territory that previously belonged to another entity.
-
B.
gainedTerritory
chosen
Indicates that one entity has acquired control over additional land or area from another entity or from a neutral state.
-
C.
heldTerritory
Indicates that one entity maintained control or possession over a specific territory or geographic area.
-
D.
acquiredTerritoryBy
Indicates a relationship where one entity gains control or ownership of a territory through a specific means, event, or process.
-
E.
lastTerritoriesConqueredBy
Indicates that the referenced territories are the most recent ones taken control of through conquest by a specified entity.
- 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_69e245b5e4208190bac8a6509867e394 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a8fedbec8190b183661edaba4cd4 |
completed | April 29, 2026, 6:45 a.m. |
| PD | Predicate disambiguation | batch_69f0621165c08190a0b27b1319733959 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 6:07 p.m.