Triple

T13852534
Position Surface form Disambiguated ID Type / Status
Subject Δίας E332979 entity
Predicate έχειΑδέλφι P363 FINISHED
Object Εστία
Η Εστία είναι η ελληνική θεά της εστίας, του οίκου και της οικογενειακής αρμονίας, μία από τους δώδεκα Ολύμπιους θεούς.
 E1065929 NE FINISHED

How this triple was built (4 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: Εστία | Statement: [Δίας, έχειΑδέλφι, Εστία]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Εστία
Context triple: [Δίας, έχειΑδέλφι, Εστία]
  • A. المائدة
    المائدة هي السورة الخامسة في القرآن الكريم، وتتناول أحكام الحلال والحرام والمواثيق والعلاقات مع أهل الكتاب.
  • B. Marcella
    Marcella is a British crime drama television series centered on a troubled former detective who returns to investigate a string of murders that echo an old case.
  • C. Plenty
    "Plenty" is a 1985 British drama film directed by Fred Schepisi, adapted from David Hare’s play about a former World War II resistance courier struggling to find meaning in postwar England.
  • D. Plenty
    Plenty is an indoor vertical farming company that uses advanced technology to grow produce more efficiently and sustainably.
  • E. The Kitchen
    The Kitchen is a Food Network daytime talk show that features chefs and hosts sharing recipes, cooking tips, and food-related conversation in a casual, collaborative format.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Εστία
Triple: [Δίας, έχειΑδέλφι, Εστία]
Generated description
Η Εστία είναι η ελληνική θεά της εστίας, του οίκου και της οικογενειακής αρμονίας, μία από τους δώδεκα Ολύμπιους θεούς.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Εστία
Target entity description: Η Εστία είναι η ελληνική θεά της εστίας, του οίκου και της οικογενειακής αρμονίας, μία από τους δώδεκα Ολύμπιους θεούς.
  • A. المائدة
    المائدة هي السورة الخامسة في القرآن الكريم، وتتناول أحكام الحلال والحرام والمواثيق والعلاقات مع أهل الكتاب.
  • B. Marcella
    Marcella is a British crime drama television series centered on a troubled former detective who returns to investigate a string of murders that echo an old case.
  • C. Plenty
    "Plenty" is a 1985 British drama film directed by Fred Schepisi, adapted from David Hare’s play about a former World War II resistance courier struggling to find meaning in postwar England.
  • D. Plenty
    Plenty is an indoor vertical farming company that uses advanced technology to grow produce more efficiently and sustainably.
  • E. The Kitchen
    The Kitchen is a Food Network daytime talk show that features chefs and hosts sharing recipes, cooking tips, and food-related conversation in a casual, collaborative format.
  • F. None of above. chosen

Provenance (5 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_69d81c5ba13c8190839315f54768acfd completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02da9460819093a3ec5a3c62ea81 completed April 14, 2026, 9:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c0f73838819085d6f052c00fc494 completed May 3, 2026, 9:41 p.m.
NEDg Description generation batch_69f7c23410dc8190972245cecfa85871 completed May 3, 2026, 9:46 p.m.
NED2 Entity disambiguation (via description) batch_69f7c3031a0c8190ad30d59fe1f2322e completed May 3, 2026, 9:49 p.m.
Created at: April 9, 2026, 10:14 p.m.