Triple
T9066495
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TAK |
E217257
|
entity |
| Predicate | relationshipToPKK |
P86765
|
FINISHED |
| Object | often described as hardline offshoot of PKK |
—
|
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: often described as hardline offshoot of PKK | Statement: [TAK, relationshipToPKK, often described as hardline offshoot of PKK]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToPKK Context triple: [TAK, relationshipToPKK, often described as hardline offshoot of PKK]
-
A.
relationshipToAllPalestineGovernment
Indicates the nature or type of relationship an entity has with the All-Palestine Government.
-
B.
relationshipToMuhajirun
Indicates the nature or type of relationship an entity has with the Muhajirun (the early Muslim emigrants from Mecca).
-
C.
relationToCouncil
Indicates the nature or type of connection an entity has with a council, such as membership, oversight, affiliation, or governance relationship.
-
D.
relationshipToUNITAF
Indicates the specific type or nature of an entity’s relationship or affiliation with UNITAF.
-
E.
relationToKhalidIbnAlWalid
Indicates a relationship or association that an entity has with Khalid ibn al-Walid.
- 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_69ca83d5a7f48190b16c1e59bd43ede0 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc94bde9c08190a4f568fbccc3c3e9 |
completed | April 1, 2026, 3:45 a.m. |
| PD | Predicate disambiguation | batch_69cc65f881248190bfd220bb28a9fb5f |
completed | April 1, 2026, 12:25 a.m. |
| PDg | Predicate description generation | batch_69cc668ad3d881908a8a93a6a1d553e4 |
completed | April 1, 2026, 12:27 a.m. |
Created at: March 30, 2026, 7:11 p.m.