Triple
T2908484
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tikrit |
E63624
|
entity |
| Predicate | recapturedFromISIS |
P25496
|
FINISHED |
| Object | 2015 |
—
|
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: 2015 | Statement: [Tikrit, recapturedFromISIS, 2015]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recapturedFromISIS Context triple: [Tikrit, recapturedFromISIS, 2015]
-
A.
recaptureFromISIS
chosen
Indicates that control of an entity was regained by a party after it had previously been held or occupied by ISIS.
-
B.
wasRecapturedBy
Indicates that an entity which had previously escaped or been released was caught again by another entity.
-
C.
recapturedByDuringWWII
Indicates that an entity was taken back or regained by another entity specifically during the period of World War II.
-
D.
abductedFrom
Indicates that an entity was forcibly taken away or kidnapped from a specified location or source.
-
E.
readmissionOfSyria
Indicates the action or event of Syria being allowed to rejoin or be reinstated into a group, organization, or body from which it was previously excluded.
- 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_69ab4c44ab448190b9411324e8a1fc1d |
completed | March 6, 2026, 9:51 p.m. |
| NER | Named-entity recognition | batch_69abe0d1dcf881909b3ae58d7cdfd9cd |
completed | March 7, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69abdd19bac881908f047d616aca8438 |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 10:11 p.m.