Triple

T33431010
Position Surface form Disambiguated ID Type / Status
Subject Otto Weddigen E856129 entity
Predicate shipLostWith P176602 FINISHED
Object SM U-29
SM U-29 was a German Imperial Navy U-boat of World War I, notable for its early war successes before being sunk with all hands in 1915.
 E2057103 NE FINISHED

How this triple was built (3 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: SM U-29 | Statement: [Otto Weddigen, shipLostWith, SM U-29]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: SM U-29
Triple: [Otto Weddigen, shipLostWith, SM U-29]
Generated description
SM U-29 was a German Imperial Navy U-boat of World War I, notable for its early war successes before being sunk with all hands in 1915.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: shipLostWith
Context triple: [Otto Weddigen, shipLostWith, SM U-29]
  • A. lostToSea
    Indicates that something has been carried away or disappeared into the sea, resulting in its loss.
  • B. shipAtTimeOfDisappearance
    Indicates that a particular ship is associated with the specific time at which it disappeared.
  • C. shipwreckUse
    Indicates that an entity makes use of, interacts with, or derives benefit from a shipwreck.
  • D. shipwreck
    Indicates that a vessel has been destroyed, stranded, or severely damaged, typically at sea or near a shoreline.
  • E. shipSankIn
    Indicates that a specific ship sank (was lost or submerged) in a particular location or body of water.
  • F. None of above. chosen

Provenance (7 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_69f349709e7881908c342b4d34f555f4 completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69f6e52a6d40819084472f6072c91e9f completed May 3, 2026, 6:03 a.m.
NED1 Entity disambiguation (via context triple) batch_6a35afbdf2e08190b8ac4ee93c699859 completed June 19, 2026, 9:08 p.m.
NEDg Description generation batch_6a35b16322908190a5a690b8f266007c completed June 19, 2026, 9:15 p.m.
NED2 Entity disambiguation (via description) batch_6a35b1d9c7b48190ab188ad30885a9e4 completed June 19, 2026, 9:17 p.m.
PD Predicate disambiguation batch_69f6e3da41948190a4cfe866ce184f73 completed May 3, 2026, 5:57 a.m.
PDg Predicate description generation batch_69f6e47c13348190a10528c84a401178 completed May 3, 2026, 6 a.m.
Created at: May 1, 2026, 1:36 a.m.