Triple
T24433801
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1971 Ibrox disaster |
E616070
|
entity |
| Predicate | hasSpecificSite |
P5003
|
FINISHED |
| Object |
Stairway 13
Stairway 13 was a notorious exit stair at Glasgow’s Ibrox Stadium long associated with dangerous overcrowding and fatal crushes, culminating in its role as the focal point of the 1971 Ibrox disaster.
|
E1633805
|
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: Stairway 13 | Statement: [1971 Ibrox disaster, hasSpecificSite, Stairway 13]
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: Stairway 13 Triple: [1971 Ibrox disaster, hasSpecificSite, Stairway 13]
Generated description
Stairway 13 was a notorious exit stair at Glasgow’s Ibrox Stadium long associated with dangerous overcrowding and fatal crushes, culminating in its role as the focal point of the 1971 Ibrox disaster.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpecificSite Context triple: [1971 Ibrox disaster, hasSpecificSite, Stairway 13]
-
A.
isSiteSpecific
Indicates that something is designed, intended, or valid only for a particular location, context, or site and does not generally apply elsewhere.
-
B.
containsSite
chosen
Indicates that one entity spatially or structurally includes another entity as a site or location within its bounds.
-
C.
hasTypeSiteFor
Indicates that one entity serves as the specific site or location designated for a particular type or category of another entity.
-
D.
hasSiteCode
Indicates that an entity is associated with a specific site identifier or code used to distinguish its location or facility.
-
E.
hasFindingSite
Indicates that a particular finding, observation, or abnormality is located in or associated with a specific anatomical site.
- F. None of above.
Provenance (6 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_69e2d7ec44b081909ccaf1f3bbec0641 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f2978469a081909f17b6955809bbef |
completed | April 29, 2026, 11:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0fe37841808190b020f8605ebe54c2 |
completed | May 22, 2026, 5:02 a.m. |
| NEDg | Description generation | batch_6a0fe3f19fec81909b7dd2fd9975336e |
completed | May 22, 2026, 5:04 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0fe46b72b48190b2c0d2d9ddaf3107 |
completed | May 22, 2026, 5:06 a.m. |
| PD | Predicate disambiguation | batch_69f287d3237c819099559c00f83131d8 |
completed | April 29, 2026, 10:36 p.m. |
Created at: April 18, 2026, 2:16 a.m.