Triple
T16332995
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Benjen Stark |
E396601
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Stark |
E149830
|
NE 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: Stark | Statement: [Benjen Stark, familyName, Stark]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stark Context triple: [Benjen Stark, familyName, Stark]
-
A.
Stark
chosen
Stark is a common surname of Scottish origin associated with various notable figures in politics, science, and popular culture.
-
B.
Stal
Stal is the commonly used short name and nickname of the Polish football club Stal Mielec.
-
C.
Stark Resilient
Stark Resilient is a cutting-edge technology and engineering company founded and led by Tony Stark in the Marvel Comics universe, focusing on advanced, sustainable innovations.
-
D.
Stange
Stange is a rural municipality in Innlandet county, Norway, known for its agricultural landscape and proximity to the town of Hamar.
-
E.
Stahl
Stahl is a surname of German origin borne by various notable individuals across fields such as sports, politics, and the arts.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d87f255b788190a400eba031dd85d8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2c4e0b1388190824b286e8452fb32 |
completed | April 17, 2026, 11:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0026173dc081909e00f6647d1f68b3 |
completed | May 10, 2026, 6:30 a.m. |
Created at: April 10, 2026, 5:07 a.m.